Book Changelog

This Machine Learning Systems textbook is constantly evolving. This changelog automatically records all updates and improvements, helping you stay informed about what’s new and refined.

Changelog

πŸ“… 2025

June 10

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: Page links for SocratiQ were updated and documentation for the SocratiQ AI learning companion was added
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: The SocratiQ AI feature has been removed and minor grammatical and content errors have been corrected
  • β–ˆβ–‘β–‘β–‘β–‘ About: SocratiQ page links were updated
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 3: DL Primer: Resource sections were added to the chapter, the distinction between training and inference was clarified, and several figures were incorporated
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 4: DNN Architectures: Resource sections were added to the chapter content, text processing in QMD files was improved, and explanations of deep learning architectures were refined
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 5: AI Workflow: This chapter now includes resource sections, benefits from improved text processing in QMD files, features enhanced clarity and consistency, and incorporates new figures
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: This chapter now includes a data pipeline overview diagram, utilizes TikZ for diagrams instead of Mermaid, and removes a broken web scraping Colab link
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 9: Efficient AI: Resource sections were added to the chapter content, text processing in QMD files was improved, and the compute-optimal scaling frontier was clarified
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 10: Model Optimizations: This update clarifies pruning strategies, incorporates resource sections into the core content, and refines the documentation on model optimization techniques
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 13: ML Operations: Resource sections were added to the chapter, MLOps content was updated for clarity and accuracy, and the operations diagram and text were revised
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 14: On-Device Learning: The chapter now includes resource sections, the equations for adapter-based adaptation are clarified, and explanations and concepts have been refined
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 18: Robust AI: This update includes resource sections, enhanced text processing within QMD files, and a new figure environment for error masking
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 15: Security & Privacy: Added a threat mitigation flow diagram, illustrated model theft attack types, and included an ML lifecycle threat diagram
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 16: Responsible AI: Expanded the Responsible AI chapter with new sections on governance structures, safety and robustness considerations, privacy architectures, fairness constraints, system explainability, deployment contexts, and detailed discussions on privacy, data governance, fairness, and explainability/transparency
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 19: AI for Good: Resource sections were added to the chapter, text processing in QMD files was improved, and the AI for Good content was refined for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction chapter now includes updated content, added footnotes, corrected minor grammatical errors, and refined language for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Resource sections were added to the chapter content, the TinyML example callout was removed, and minor grammatical and content errors were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Resource sections were added to the chapter content, text processing in QMD files was improved, and figure references along with a parallelization typo were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Resource sections were added to the chapter content, text processing in QMD files was improved, and the explanation of activation checkpointing was clarified
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Resource sections were added to the chapter, placement and allocation definitions were clarified, and code block language was corrected for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Resource sections were added to the chapter content, text processing in QMD files was improved, and a typo in the benchmarking documentation was fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Resource sections were added to the chapter content, minor grammatical and content errors were corrected, and text processing in QMD files was improved
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Grove Vision Ai V2: The Grove Vision AI V2 lab now includes improved documentation and a new lab exercise
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Setup And No Code Apps: A new lab on Grove Vision AI v2 has been added and the existing documentation has been improved with fixes for typos and increased clarity
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Arduino Image Classification: A new lab demonstrating image classification with Grove Vision AI V2 has been added along with improvements to the Grove Vision AI V2 documentation
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Arduino Object Detection: A new lab has been added demonstrating object detection using the Grove Vision AI v2 module on an Arduino
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Lab Setup: The lab setup instructions were updated, links to required software were added, and minor typos were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs Overview: The lab file templates were updated and instructions for using Jupyter notebooks were added
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Image Classification: A typo was corrected in the image classification lab instructions

May 14

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The on-device learning content has been refactored and clarified for improved understanding

May 14

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The on-device learning content has been refactored and clarified for improved understanding

May 04

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 5: AI Workflow: The chapter now includes updated explanations of data preprocessing and a new section on model evaluation metrics
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: The chapter now includes updated examples for data pipelines and a new section on cloud-based data engineering tools
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 10: Model Optimizations: The chapter now includes updated explanations of gradient descent variants and additional examples demonstrating momentum optimization techniques
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 11: AI Acceleration: The discussion on hardware acceleration has been refined, the explanation of hardware specialization has been enhanced, and the explanation of AI compute primitives has been clarified
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 13: ML Operations: The chapter now features consolidated TikZ figure styling, expanded MLOps core concepts and case studies, and corrected acronym usage
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 14: On-Device Learning: This update includes a new Federated Learning section, explores on-device learning strategies for limited data scenarios, and expands the discussion on security considerations in on-device learning
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction has been updated with improved content and clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The dimension order for W^L was swapped and a script was added to identify any missing references
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: The chapter now includes a script to identify and address any missing references within the text
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Content from Chapter 6 was integrated and various fixes were implemented
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Minor issues were fixed and label checking was improved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter’s β€œPurpose” heading was renamed to β€œMotivation”, benchmarking metrics and power measurements were clarified, and a script was added to identify missing references
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: Implemented label checking fixes and a script to identify missing references
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Minor issues were fixed and label checking was improved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Figure styling was consolidated using TikZ and a script was created to identify missing references
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The PlantVillage Nuru footnote accuracy was updated and a script was added to locate any missing references
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: The wake-word detection footnote was formatted, a redundant footnote definition was removed, and the grammar in the GDPR/HIPAA footnote was corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 9: Efficient AI: Bravo fixed several errors in the text of Chapter 9
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Arduino Keyword Spotting: Fixed keyword recognition accuracy issues, updated code for better performance, and added explanations for model training parameters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Raspi: Updated Raspberry Pi setup instructions, added code for an image classification task, and improved the troubleshooting guide
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Raspberry Pi Setup: The Raspberry Pi setup instructions were updated with links to the latest software versions and added troubleshooting tips
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: The Nicla setup instructions were updated for improved clarity and accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: The lab’s formatting, wording, instructions, documentation, text content, and images have been updated for clarity and accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Object Detection: The lab now includes formatting updates, clearer instructions, and an updated object detection model
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: The code example was corrected and the instructions for connecting the NICLA Vision board were updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Xiao Esp32S3: The Xiao Esp32S3 lab content has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Setup: Updated instructions for flashing firmware, added troubleshooting tips, and included links to Seeed documentation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Image Classification: Fixes were made to the LABS part 2_seeed_xiao_esp32s3
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Object Detection: The XIAO Object Detection lab has been updated with changes to LABS part 2_seeed_xiao_esp32s3
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Keyword Spotting: The XIAO keyword spotting lab code has been updated and accompanied by explanations for the modifications
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Motion Classification: The XIAO Motion Classification lab now includes updated code and explanations for sensor data processing
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Image Classification: The Raspberry Pi image classification code was updated and accompanied by explanations for the modifications
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Object Detection: The object detection lab now includes updated code and explanations for setting up a Raspberry Pi
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Large Language Models: The Raspberry Pi labs section has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Vision Language Models: The VLM lab guide was refactored for improved clarity and the LABS part_raspi was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Dsp Spectral Features Block: The LABS part_shared has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Kws Feature Eng: The shared LABS section has been updated

March 26

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: An exercise reference was removed and another was corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 18: Robust AI: Package commands were fixed, Helvetica font was added, and line commands were corrected

March 25

πŸ“„ Frontmatter
  • β–ˆβ–‘β–‘β–‘β–‘ Foreword: The foreword has been updated based on feedback from vale testing
  • β–ˆβ–‘β–‘β–‘β–‘ About: The book underwent vale testing for improvements
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The contributors list has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ SocratiQ: Trailing whitespace was removed and all broken links were fixed
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 9: Efficient AI: A new Scaling Laws section was added to the chapter, section headers were updated, and epoch AI figures were included
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 13: ML Operations: The MLOps key components section was updated, embedded Operations were replaced with Operational design principles, and references were added
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 18: Robust AI: The chapter now includes an expanded attacks section, a more detailed real-world applications section, an introductory paragraph, and a discussion on shifts in adversarial examples
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction chapter now has consistent footnote naming and removed unnecessary code and packages for a cleaner build process
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Fixed hyphenation issues, corrected a typo impacting PDF generation, standardized Markdown styles, incorporated footnotes for improved clarity, and addressed inconsistencies in footnote naming
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: Hyphenation is now handled globally, colons are consistently formatted, and all broken links and missing figure references have been corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: A definition was added and references were updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The chapter now uses consistent hyphenation, has updated markdown styles, includes a mermaid diagram, and features several text edits for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: A figure illustrating ONNX was added, footnote naming conventions were standardized, and the callout format was corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Footnote naming was standardized, missing figure references were fixed, and section headers were reviewed for consistency
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The chapter received spelling and stylistic improvements, including added footnotes and corrected figure references, along with a fix for broken links
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The chapter received spelling corrections, updated Markdown styles for consistency, and improved footnote and figure reference formatting
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter now has corrected links, updated section headers, and a resolved missing figure reference
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The chapter’s markdown styling was cleaned up and all broken links were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Markdown styles were cleaned and all broken links were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The chapter’s markdown formatting has been cleaned up and all broken links have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: This update includes a plot and discussion on Jevon’s paradox, along with fixes for broken links within the chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The chapter now has consistent footnote naming, fixed broken links, and improved Markdown styling with the addition of a new definition
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 20: Conclusion: Dangling sections were removed and the conclusion underwent a first round of editing
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter: Old Sus Ai: The chapter content has been updated and an outdated file removed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 3: DL Primer: Markdown styles were cleaned, a definition was added, footnotes were updated for consistency, and footnote naming conventions were standardized
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter: Generative Ai: The Generative AI chapter received its initial draft
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: The Arduino setup instructions now have consistent Markdown styling and all links are functional
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: The lab’s Markdown formatting was cleaned up and all broken links were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Vision Language Models: The lab’s Markdown formatting has been standardized and all broken links have been repaired
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: Markdown styles were cleaned up in the image classification lab
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Keyword Spotting: The Markdown styles in the file have been cleaned up
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Image Classification: Spelling mistakes have been fixed throughout the lab
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Keyword Spotting: Spelling errors were fixed and Markdown styles were standardized for consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Motion Classification: The lab’s Markdown formatting has been updated for improved readability and style consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Raspberry Pi Setup: Spelling mistakes were fixed using codespell check
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Object Detection: The object detection lab’s Markdown file now has fixed links and improved styling
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Large Language Models: Markdown styles were cleaned up throughout the file
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Kws Feature Eng: Markdown styles were cleaned up throughout the lab
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Dsp Spectral Features Block: Corrected spelling errors and standardized markdown formatting
πŸ“š Appendix
  • β–ˆβ–‘β–‘β–‘β–‘ PhD Survival Guide: The PhD Survival Guide now has corrected spelling and all broken links have been resolved

March 03

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: Callout titles are now formatted correctly and QMD file linting has been addressed
  • β–ˆβ–‘β–‘β–‘β–‘ About: Header spacing has been adjusted for consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The contributors list has been updated and reflected in the readme and acknowledgements file
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–ˆβ–‘ Chapter 10: Model Optimizations: This chapter now includes sections on structured optimization, post-training quantization (PTQ) and quantization aware training (QAT), sparsity visualization techniques, knowledge distillation (KD) figures, and learning transfer hardening (LTH) along with iterative pruning and calibration
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 11: AI Acceleration: This update includes a new section on hybrid mapping strategies and a plot comparing model performance to memory bandwidth. The chapter overview and definition have also been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Fixed callout title formatting and resolved issues with QMD file linting
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: Formatting and linting improvements were made to the DL Primer chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: Callout title formatting and QMD file linting were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Redundant definitions were removed, text errors were corrected, and QMD file linting was fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Formatting and code issues were addressed to improve readability and functionality
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Added model and data parallelism images for distributed execution, removed redundant definitions, and updated the chapter by removing an unnecessary log file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Descriptions of single and multi GPU systems were added, redundant definitions were removed, and MD formatting issues were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Redundant definitions were removed, spacing issues were fixed, and QMD file linting was improved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter now uses tikz code for images, includes a new image illustrating datacentric AI, and has corrected a broken reference and citation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Definitions were streamlined, callout titles are now correctly formatted, and QMD file linting issues have been resolved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: Redundant definitions were removed and various formatting issues in Markdown, callouts, and general text were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Definitions were removed, markdown formatting was fixed, and callout titles were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Definitions were removed, callout titles were formatted correctly, and QMD file linting was fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: Definitions were removed, callout titles were formatted correctly, and QMD file linting was fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: Markdown formatting and linting were addressed in the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: Typos were corrected, redundant definitions were removed, and callout titles were formatted correctly
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 16: Responsible AI: Callout title formatting and QMD file linting were fixed
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Nicla Vision: The Nicla Vision LABS section has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: The Arduino setup section for the nicla_vision LABS has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: The Arduino image classification lab has been updated with changes to the arduino/nicla_vision LABS section
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Object Detection: The Arduino object detection lab has been updated with the latest changes to the arduino/nicla_vision repository
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Keyword Spotting: The Arduino/Nicla Vision LABS section has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: The Arduino motion classification lab content was updated and header spacing was improved for consistency
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Vision Language Models: The lab now has corrected markdown formatting, improved linting for QMD files, and adjusted header spacing
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Kws Feature Eng: The lab now has corrected markdown formatting and resolved linting errors in the QMD files
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Labs Overview: Linting errors in QMD files were corrected

February 08

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list has been updated to include all contributors and correct any omissions
  • β–ˆβ–‘β–‘β–‘β–‘ SocratiQ: Included a link to the Socratiq research paper

February 07

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Index: The precheck now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ About: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Changelog: The changelog is now automatically generated and formatted within the frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: The SocratiQ precheck now only runs on qmd and bib files
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a list of contributors and the readme has been updated to reflect this
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 12: Benchmarking AI: The chapter now includes MLPerf power trends data, a FastML science graph visualization, and updated benchmarking challenges with new plots and graphs to motivate the importance of benchmarking
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The code now directly uses _quarto.yml and the precheck script is limited to qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The ML Systems chapter content was updated and the precheck script now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The precheck script now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The precheck function now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The code now relies solely on _quarto.yml and the precheck function is limited to qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Figure formatting was fixed, a diagram was updated, and an unused library was removed from the code
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: The code now uses _quarto.yml instead of an in-use library, a bib reference was corrected, and R code was added for debugging and visualization purposes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The precheck now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The code now uses _quarto.yml for library management, PNG images are cached locally, and the precheck script only runs on qmd and bib files
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: The precheck now only runs on .qmd and .bib files
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Keyword Spotting: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Setup: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Image Classification: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Object Detection: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Keyword Spotting: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Motion Classification: The precheck script now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspi: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspberry Pi Setup: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Image Classification: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Object Detection: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Large Language Models: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Vision Language Models: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Shared: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Kws Feature Eng: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Dsp Spectral Features Block: The precheck script now only runs on qmd and bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Lab Setup: The precheck script now only runs on .qmd and .bib files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs Overview: The precheck script is updated to run only on .qmd and .bib files
πŸ“š Appendix
  • β–ˆβ–ˆβ–‘β–‘β–‘ PhD Survival Guide: The precheck now only runs on .qmd and .bib files

February 02

πŸ“„ Frontmatter
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a list of contributors
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 12: Benchmarking AI: The chapter now features improved learning objectives, a corrected table, updated references, reorganized content, and an updated case study
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: All ###* callout titles have been converted to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: All callout ###* titles have been updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: All callout ###* titles have been updated to use a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: Errata were fixed and all callout ###* titles were updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: All ###* callout titles have been updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: All callout ###* titles have been updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The way TikZ packages are used in the chapter has been restructured by moving their declaration outside of begin{..} blocks and into a header file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Figure 8.8 was updated and several new diagrams were added to enhance visual understanding. Python code was also corrected for accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Callout titles were updated to a title block format, the bibliography was updated, and an incorrect entry was removed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: All ###* callout titles have been updated to use a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: All ###* callout titles have been updated to use a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: All ###* callout titles have been updated to use a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: All callout ###* titles have been updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: All callout ###* titles have been updated to use a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: All callout ###* titles have been updated to use a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: All callout ###* titles have been updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: All ###* callout titles have been updated to a title block format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: All callout ###* titles have been updated to a title block format

September 20

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 11: AI Acceleration: Character formatting was fixed, figure references were corrected, and all chapters are now complete
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 5: AI Workflow: References were fixed and all chapters were revised
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: Fixed a broken link to a video and corrected instances of ’ being used instead of ’, while also completing revisions for all chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Character formatting was fixed, formatting was improved, and figure references were added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Figure references were fixed and all references to embedded AI were removed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Figure references were fixed and all chapters are now complete
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: References were fixed, a path was corrected, and all chapters are now complete
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Figure references were fixed and all chapters are now complete
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Figure references were fixed and all chapters were updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Merge conflicts were resolved and figure references were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter’s formatting was improved, some figures were removed, and merge conflicts were resolved
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 19: AI for Good: References and figure citations were corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: Corrected single quotes to apostrophes throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: Corrected instances where single quotation marks were used inconsistently with apostrophes
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 17: Sustainable AI: Figure references were corrected and typos in the sustainability section were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: Figure references were corrected throughout the chapter
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: The lab code has been fixed by BravoBaldo
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Setup: Fixes were implemented to improve the XIAO ESP32S3 setup process
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Image Classification: The output format for the lab has been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Object Detection: The lab received fixes and improvements contributed by BravoBaldo
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Keyword Spotting: Fixes were implemented to improve the accuracy and efficiency of the keyword spotting model
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspberry Pi Setup: Character formatting was fixed and additional files were added to the lab setup
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Lab Setup: Lab setup instructions have been corrected for accuracy and clarity
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Object Detection: Fixes were implemented by BravoBaldo
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Motion Classification: An image was fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Raspi: Fixes were implemented by BravoBaldo
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Image Classification: Character formatting was fixed and typos were corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Object Detection: Typos have been corrected

September 12

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The chapter content has been revised based on feedback from Baldo
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: The chapter now includes corrections and improvements addressing robustness concerns in AI models
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: The conclusion has been revised based on feedback
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 19: AI for Good: The chapter contains various fixes
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 17: Sustainable AI: A quote’s indentation was fixed and formatting was improved throughout the chapter
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Object Detection: The Object Detection Lab files have been uploaded for use with Raspberry Pi
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Image Classification: A link and some typos were corrected

September 06

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 16: Responsible AI: The bibliography and text were corrected for accuracy

September 04

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The chapter contains grammar fixes and improved explanations for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: The explanations in Chapter 9 have been refined for better clarity
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 1: Introduction: Captions for even side pages have been corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 15: Security & Privacy: The chapter received bug fixes and grammar improvements
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 19: AI for Good: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 12: Benchmarking AI: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: Grammar errors were corrected throughout the conclusion chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 3: DL Primer: Grammar errors were corrected for improved readability
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: The chapter contains grammar fixes for improved clarity
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: The chapter contains grammar fixes for improved clarity
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 16: Responsible AI: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 18: Robust AI: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 17: Sustainable AI: Grammar errors were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: Grammar errors were corrected throughout the chapter
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: The lab now contains grammar corrections for improved readability
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Kws Feature Eng: Grammar was corrected throughout the lab

September 02

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 13: ML Operations: The ML Operations chapter now includes a new section on model serving and has been updated with improved content and corrected errors
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The chapter now includes a table fix, more student-focused explanations of hardware design principles, and an introduction
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: A dangling sentence was corrected
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspberry Pi Setup: The Raspberry Pi setup instructions were updated and additional files were included for the lab setup
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Image Classification: Files were added to the lab

August 29

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The ML Operations chapter has been updated with corrections based on feedback
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The chapter received fixes based on feedback from (BravoBaldo?)
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs: Resolved an issue with merging tables
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Image Classification: Files were added to the lab
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Kws Feature Eng: Formatting issues were fixed

August 27

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 10: Model Optimizations: The knowledge distillation explanation was improved, the challenges were adjusted to be less repetitive and more informative, and the explanations of structure importance methods were corrected
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 9: Efficient AI: Duplicate information between chapters 8 and 9 was removed, background about floating point representation was added, and explanations of structure importance methods were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Benchmarking AI chapter now includes corrections for improved accuracy and clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Fixed broken links and improved table formatting in the AI Frameworks chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The Power Attack and Side-Channel Attack sections were edited and broken links were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: This update addresses several issues including broken links, inaccurate information about qbits, hyphen errors, a duplicate title, and a grammatically incorrect sentence
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: Minor wording changes were made for improved clarity and flow
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 17: Sustainable AI: Broken links in the chapter have been fixed
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Xiao Esp32S3: Table formatting for grid tables has been fixed

August 22

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 19: AI for Good: A section on AI for climate change mitigation was added, the disaster response case study was updated, and new ethical considerations related to AI for good were included
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 11: AI Acceleration: Added a section on systolic arrays for matrix multiplication, updated the discussion of tensor cores to reflect the latest NVIDIA architectures, and clarified the impact of memory hierarchy on AI performance
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 17: Sustainable AI: A new section on ethical considerations in sustainable AI was added, existing content on data efficiency techniques was updated, and a case study on responsible AI development was included
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs: Lab files were added to the textbook
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspi: Files were added to the Raspi lab
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspberry Pi Setup: Files were added to the Raspberry Pi Setup lab

August 21

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Dsp Spectral Features Block: Removed unused code from the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: Dead code was removed from the lab
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: Typos were corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: Typos were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: Typos were fixed throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 11: AI Acceleration: Typos were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: Typos were corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: Typos were corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 15: Security & Privacy: Typos were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: Inconsistent bold text was removed for improved readability
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: A minor typo was corrected
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Raspi: This lab introduces a hands-on experience with Raspberry Pi for machine learning applications
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Raspberry Pi Setup: This lab now includes initial instructions for setting up a Raspberry Pi for machine learning tasks
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Pi Image Classification: This lab introduces a basic image classification pipeline using a Raspberry Pi
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Pi Object Detection: This lab introduces object detection using a Raspberry Pi
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs: The lab section now includes a fixed table format and an initial version of the rasPi lab
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Large Language Models: This lab introduces a basic implementation of a large language model on a Raspberry Pi
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Lab Setup: The lab now includes initial instructions for setting up a Raspberry Pi environment

August 15

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 11: AI Acceleration: Table references were fixed for accuracy
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: Table references were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 15: Security & Privacy: Table references were fixed for accuracy

August 15

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: Several pivotal fixes and enhancements were made to clarify and improve the data engineering content
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: A citation reference was fixed and tables were given striped and hover styles
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Tables now have striped and hover styling, centering has been fixed, and the grid table has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The table in this chapter has been updated to a grid format and several fixes have been implemented for clarity and accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: A reference was corrected, a broken Colab link was fixed, and table formatting was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The AI for Good chapter has been enhanced
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter now includes fixes for existing code examples and enhanced explanations of various benchmarking metrics
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The chapter includes various enhancements and bug fixes for improved clarity and accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Several errors were fixed and explanations were improved for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The chapter now includes fixes related to delve and enhancements that utilize framework examples
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The chapter’s tables were converted into grid tables and updated for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: Improved Arduino code examples and corrected small errors in the image classification implementation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Several issues were fixed and explanations were enhanced for clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Implemented pivotal fixes and enhancements to improve clarity and accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The chapter now includes a grid table and has been corrected for errors
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The chapter’s content has been refined with corrections, clearer explanations, and updated terminology
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The table in this chapter has been updated to a grid format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The chapter now includes various fixes, improved utilization of concepts, and a more in-depth exploration of existing fixes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The AI Workflow chapter now includes several fixes and expanded explanations of key concepts
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: The Arduino Image Classification lab has been enhanced
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Image Classification: Delve fixes were implemented
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Keyword Spotting: The lab now utilizes

August 15

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 8: AI Training: The chapter now includes a discussion of regularization techniques and hyperparameter search methods, consolidates information on common training pitfalls, and updates the neural network notation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: The chapter was updated with changes incorporated from the β€˜dev’ branch
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: Typos were corrected throughout the chapter

August 06

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 7: AI Frameworks: The chapter now focuses more on advanced features while removing the federated learning section. Table formatting has been improved for better readability and consistency
  • β–ˆβ–ˆβ–‘β–‘β–‘ Dsp Spectral Features Block: Resolved image width problems to ensure proper display in PDF format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: Image width issues were fixed for PDF rendering, redundant underlines were removed, and all broken video links were repaired
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The chapter now features corrected URL links, updated table formatting for a grid layout, and consistent credit attribution style
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: Tables were updated with grid formatting, source attributions were revised, and builds for HTML and PDF were implemented
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Tables now use grid formatting and are left-aligned, incorporating student feedback
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: Fixed all broken URL links in the chapter, updated the β€œCredit” section to be consistent with β€œSource”, and added grid tables formatted with left alignment
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The text was updated slightly and a new Wake Vision Colab exercise was added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The privacy and security section was edited and broken links were fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: Fixed all broken URL links, updated credit sources with consistent formatting, and added HTML and PDF builds compatible with Edward Tufte’s style guide
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: All broken URL links were fixed and the credit source formatting was updated to be consistent
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: All broken URL links were fixed and table formatting was updated to use left alignment with markdown. The β€œCredit” section was renamed to β€œSource” and the formatting style was made consistent
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: All broken URL links were fixed, credit sources were updated with consistent formatting, and an HTML + PDF build was added for Edward Tufte
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: All broken URL links were fixed, source citation formatting was updated, and grid tables with left-aligned markdown formatting were added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Grid tables were added to the chapter, all tables are now left-aligned, and image paths and figure IDs were updated for consistency
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Grid tables were added to the chapter, all tables are now left-aligned, and source attributions were updated with consistent formatting
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: Implemented grid tables for better visualization, aligned all tables with markdown formatting, and added in-text citations for sources
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Source citations were updated and formatting was made consistent across the chapter. Additionally, HTML and PDF builds were created
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The textbook now has HTML and PDF output formats
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 12: Benchmarking AI: Credit attributions were updated and formatting was corrected for consistency
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Nicla Vision: Tables are now left-aligned and credit information is consistently formatted as β€œSource”
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: Image width issues were fixed to improve PDF rendering and redundant underlines were removed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: Image width issues were fixed for PDF rendering, redundant underlines were removed, and remaining broken video links were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Object Detection: Image width issues for PDF rendering and broken video links have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Keyword Spotting: Image width issues were fixed to improve PDF rendering and all broken URL links were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: Image width issues affecting PDF rendering have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Setup: Image widths were adjusted to prevent rendering issues in PDFs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Image Classification: Image width issues affecting PDF rendering have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Object Detection: Image width issues affecting PDF rendering have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Keyword Spotting: Image width issues were fixed for better PDF rendering and broken links were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Motion Classification: Image width issues that affected PDF rendering have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Dsp Spectral Features Block: Image width issues affecting PDF rendering have been fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Xiao Esp32S3: Credit attributions were updated and formatting was made consistent
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Shared: All tables in this lab now use markdown formatting with left alignment
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Kws Feature Eng: Image widths were adjusted to ensure proper rendering in PDFs

June 25

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 3: DL Primer: The link for video 3.1 has been corrected

June 20

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The chapter now includes corrections to a broken reference and incorporates feedback from students on the β€˜dev’ branch
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Shared: Broken links were fixed

June 19

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Object Detection Fomo: Labs have been integrated into the Object Detection Fomo chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: A figure illustrating MLPerf training progress was added, and the chapter content was updated based on feedback. Formatting and line spacing were also corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Citation formatting was changed from parentheses to brackets, MD lint fixes were implemented, and a link to Google’s Edge TPU website was added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction material was updated and the foreword content was removed to correct an error
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The chapter content has been refined and improved based on feedback and data review
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: Citation formatting was changed from parentheses to square brackets and minor style fixes were made
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: Citation formatting was changed from parentheses to brackets and several typos were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 18: Robust AI: Citation formatting was changed from parentheses to brackets and markdown linting issues were addressed
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements were updated with MD lint fixes and some comments were disabled on specific pages
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 19: AI for Good: Applied Markdown linting fixes for improved formatting and consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: Applied Markdown linting fixes for consistency and readability
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 3: DL Primer: The chapter contains a batch of typographical errors and formatting issues that have been corrected
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 9: Efficient AI: Markdown lint errors were fixed and a missing video link was added
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: The chapter contains a batch of typo and format fixes
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: The lab notebook underwent code style and formatting improvements using MD lint
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: Applied markdown linting fixes to the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: Applied Markdown linting fixes for consistency and style
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 15: Security & Privacy: The case study header was fixed and some markdown linting issues were resolved
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 16: Responsible AI: The Markdown code was cleaned up using a linting tool
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 17: Sustainable AI: Applied Markdown linting fixes for improved formatting and consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: This chapter contains a batch of typo and format fixes
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 5: AI Workflow: The Markdown files were cleaned up using a linting tool
  • β–ˆβ–‘β–‘β–‘β–‘ Dsp Spectral Features Block: The resources were fixed and the title was adjusted
  • β–ˆβ–‘β–‘β–‘β–‘ Generative Ai: The wording of several passages has been refined for clarity
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Labs: The lab section was reorganized, the overview was updated, a table was transposed and updated, and labs were integrated into the main text
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Arduino Image Classification: This update integrates all Arduino lab files into the curriculum and fixes resource links
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Nicla Vision: The lab now includes KWS, has improved introductory text, updated images, and corrected build errors
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: Resources were fixed, some elements were renamed, and the setup content was integrated into the lab structure
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Object Detection: Resource links were fixed and the object detection lab was integrated into the existing labs section
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Keyword Spotting: The lab now has correctly placed content, improved grammar (β€œcodes” changed to β€œcode”), and updated resources
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: Content placement was corrected, grammar was improved, and the lab was integrated into the curriculum
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Xiao Esp32S3: The lab now has a streamlined introduction, corrected build errors, includes proper image attribution, and is better integrated within the overall lab structure
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Setup: Resources were fixed, SEEED labs were imported, and files were renamed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Image Classification: The lab now imports SEEED labs and integrates them into the existing content, with resource links also being fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Object Detection: The lab now incorporates resources and imports from the SEEED labs while addressing MD lint issues
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Keyword Spotting: Resources were fixed, SEEED labs were imported and integrated into the lab exercises
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: XIAO Motion Classification: This lab now includes links to internal documentation and integrates with other SEEED labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Shared: Added an overview section for the shared labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Kws Feature Eng: The lab now includes MD lint fixes, updated resources, and is integrated into the broader lab structure
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Dsp Spectral Features Block: The lab block’s title was slightly adjusted and integrated into the broader lab environment
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Lab Setup: Added getting started content to the lab setup and updated the overview section with a placeholder for detailed information

June 11

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 18: Robust AI: The chapter now includes video callouts, reorganized exercise callouts, updated references and links, an expanded general description, and information about Bayesian Neural Networks
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Video callouts were added to the chapter along with end-of-section resource recommendations, and formatting and spacing issues were resolved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual appeal
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Video callouts were added to the chapter, a previous .callout issue was fixed, and spacing and formatting of exercise callouts were improved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual appeal
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: Video callouts were added and end-of-section resources were updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Video callouts and end-of-section resources were added, and a previous .callout issue was fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Video callouts were added to the chapter and exercise callout blocks were folded for improved aesthetics
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual presentation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: Video callouts were added and exercise callout blocks were folded for improved visual presentation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual appeal
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: Video callouts were added to the chapter and exercise callout blocks were folded for improved visual presentation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Video callouts were added and exercise callout blocks were folded for improved visual presentation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: Video callouts and end-of-section resources were added to the chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Video callouts and exercise callout blocks were added and formatted for improved readability
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Video callouts were added, exercise callout blocks were folded for improved aesthetics, and a table rendering issue was fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Video callouts were added to the chapter and a previous formatting issue with .callout was fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Generative Ai: Added text about future generative AI content and made minor edits to existing β€œcoming soon” sections

June 01

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The Colab badge was fixed, the β€œcoming soon” section now uses bullets, and the slide notes use the default format for better PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The Colab badge was fixed, the β€œcoming soon” section now uses bullets, and the default note for slides was implemented for better PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The Colab badge was fixed, the β€œcoming soon” section was updated with bullets, and minor markdown issues were corrected in the text and URL highlighting
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The Colab badge is now fixed, the β€œcoming soon” section uses bullets instead of a paragraph, and the default note for slides has been changed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The Colab badge was fixed, the β€œcoming soon” section was updated with bullets, and the default slide note was changed to render better in PDFs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The Colab badge was fixed, the β€œcoming soon” section was updated with bullets, and the default note for slides was changed to render better in PDF
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The Colab badge was fixed, rendering issues were resolved, and the β€œcoming soon” section’s formatting was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The Colab badge was fixed, the β€œcoming soon” section was updated to use bullets, and slide note formatting was changed for better PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The Colab badge was fixed, the β€œcoming soon” section now uses bullets, and the default note for slides was changed for better PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The Colab badge was repaired, the β€œcoming soon” section was updated to use bullets, and the default note for slides was changed to render better in PDF
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The Colab badge was fixed, the β€œcoming soon” section now uses bullets, and the slide notes use the default format for better PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: Resolved Colab badge display problems, implemented (exr?)- notation for Colab notebooks, and optimized slide rendering for PDFs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The Colab badge was fixed, the β€œcoming soon” section was updated with bullets, and formatting was improved for labs, exercises, and slides
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The Colab badge was fixed, the β€œcoming soon” section was updated to use bullets, and the default slide note was changed to render better in PDFs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Fixed rendering problems, corrected some headers, and set a default note for slides to ensure proper PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The coming soon section now uses bullets, slide notes utilize the default format for better PDF rendering, and formatting was adjusted in labs, exercises, and slides
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The coming soon section now uses bullets, the slide default note was changed for better PDF rendering, and formatting was adjusted in labs, exercises, and slides
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Reference links were re-added to the introduction section and the grammar and readability were improved
  • β–ˆβ–‘β–‘β–‘β–‘ Generative Ai: Fixed rendering problems in the chapter

May 26

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 10: Model Optimizations: This update includes added videos, updated exercises, and additional slides for a more comprehensive learning experience
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 18: Robust AI: The Robust AI chapter now includes learning objectives and updated figures, incorporating feedback from Yanjing for improvements
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 14: On-Device Learning: This chapter now includes videos, additional collaborative exercises, and updated content based on recent slides
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 20: Conclusion: The conclusion section was updated and a cover image was added to the file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: This chapter now includes short captions for all videos, an updated Data Diversity and Quality section, and a fix for SVG to PNG conversion to enable PDF builds
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The conclusion was updated, figure captions and references were fixed, and section headers were added for cross-referencing
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Section headers were added for easier cross-referencing, additional slides were incorporated, and figure captions and references were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The chapter now includes additional slides and updated content with exercises. The colab-badge.svg was also converted from SVG to PNG to enable PDF builds
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Video captions were added, section headers were implemented for easier cross-referencing, and figure captions and references were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Fixed broken slide links, added section headers for easier cross-referencing, and updated the frameworks.qmd file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Short captions were added for videos, the ops.qmd file was updated, and the colab-badge.svg was changed from SVG to PNG
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: All tables now have captions, relative path links were cleaned up, and short captions were added to the videos
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Slide links were fixed, section headers were added for cross-referencing, and the bib file header was corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: Section headers were added for easier cross-referencing, video captions were included, and the colab-badge.svg was changed to PNG to enable PDF builds
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Section headers were added for easier cross-referencing, punctuation was corrected throughout the chapter, and the colab-badge.svg was changed to PNG to enable PDF builds
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Added section headers for easier cross-referencing, fixed broken links, and updated figure captions and references
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Added section headers for cross-referencing, updated names throughout the chapter, and removed the β€œEmbedded Systems” section to focus solely on ML systems
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: Section headers were added for easier cross-referencing, a broken link was fixed, and grammatical errors were corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Generative Ai: Added section headers for easier cross-referencing and updated β€œComing soon” text to β€œComing soon”
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Section headers were added for easier cross-referencing, a bibliography file header error was corrected, and a cover image was added to the introduction chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Ml: Chapters 1 through 4 were edited and the collapse setting for the Embedded ML chapter was set to false
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Sys: Chapters 1 through 4 were edited, additional slides were included, and the collapse setting was changed
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: Image logos were added and an initial draft of the acknowledgements chapter was created
  • β–ˆβ–‘β–‘β–‘β–‘ Dsp Spectral Features Block: Corrected punctuation and replaced instances of 's with ’s
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: Punctuation has been corrected in the lab
  • β–ˆβ–‘β–‘β–‘β–‘ Kws Feature Eng: Punctuation has been corrected throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Motion Classify Ad: Fixed punctuation throughout the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Niclav Sys: Corrected punctuation throughout the chapter

March 21

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: The Resources section now includes introductory text for each part and can be collapsed, exercise callouts were added, and slides have been moved to the end of the page
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 3: DL Primer: The Resources section now includes introductory text for each part and a collapsible feature, additional slides were incorporated, and the placement of slides was moved to the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: A β€œResources” section was added to the end of all QMD files, and the existing Resources were updated with introductory text and enabled to be collapsed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: A β€œResources” section was added to the end of all QMD files with collapsible sections for each part and the slides were moved to the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: The Resources section in Chapter 9 now includes introductory text for each part and can be collapsed. Additional slides were added, and an empty β€œResources” section with headers was added to the end of all QMD files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Ml: The Embedded Ml chapter now includes additional slides placed at the end of each page, and a new Resources section with introductory text for each part
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Sys: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and slides have been moved to the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The Resources section now includes introductory text for each part and collapsible elements, while slides have been moved to the end of the page. Colab badges have also been added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The Resources section now includes introductory text for each part and can be collapsed. Empty β€œResources” sections were added to the end of all QMD files with headers
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and all slides have been moved to the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Resource sections now have introductory text and collapsible functionality, additional slides were incorporated, and slides were relocated to the end of pages
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The Resources section now includes introductory text for each part and has been moved to the end of pages. Empty β€œResources” sections have also been added to all QMD files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The Resources section now includes introductory text for each part and can be collapsed, additional slides were added, and slides have been moved to the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: A β€œResources” section was added to the end of the chapter with collapsible functionality and slides were moved to the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The Resources section now includes introductory text for each part and slides have been moved to the end of the page. An empty β€œResources” section has also been added to all QMD files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Resource sections now include introductory text and can be collapsed, additional slides were incorporated, and all slides are now located at the end of the page
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Each resource section now has introductory text, slides have been moved to the end of pages, and a new β€œResources” section has been added to all QMD files

March 12

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 7: AI Frameworks: Added Colab notebooks to the chapter and included additional slides while also fixing previous notes
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: The data engineering chapter now includes Colab notebooks, a new web scraping exercise in both the subsection and as a separate part of the exercises, and additional slides
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Removed a figure reference and a Mermaid diagram section, and made fixes to the non-ASCII checker scripts
  • β–ˆβ–ˆβ–‘β–‘β–‘ Niclav Sys: Corrected broken links and implemented non-ASCII checking scripts with fixes for related issues
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Ml: Removed debug code, added a nested example, and implemented arrow capability and custom callouts in the style file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The chapter now includes additional slides and incorporates non-( ) ASCII checker scripts with accompanying fixes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter now includes additional slides, corrected notes from the previous week, and incorporates non-ASCII checker scripts
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The chapter now includes additional slides and incorporates non-ASCII checking scripts for improved accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Sys: The chapter now includes additional slides and incorporates non-ASCII checking scripts with accompanying fixes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The chapter content was expanded with additional slides and included non-( ) ASCII checker scripts along with fixes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: More slides were added to the chapter, last week’s notes were fixed, and scripts for checking non-( ) ASCII were added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The chapter content was expanded with additional slides and corrections were made to previous notes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The Responsible AI chapter now includes additional slides and has had its style corrected to ensure proper rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Added more slides and implemented non-ASCII checking scripts with accompanying fixes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The chapter now includes additional slides, non-( ) ASCII checker scripts have been added and fixed, and style issues affecting successful rendering have been resolved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The chapter includes additional slides, corrected previous notes, and incorporates non-(ASCII) checker scripts for improved accuracy
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: Non-ASCII checker scripts were added and style issues were fixed to ensure successful rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Incorporated non-ASCII checker scripts and resolved problems with non-ASCII characters in code examples

February 03

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Unpopulated list items were removed and the styling of list items was made more consistent
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The MCU example for a smartwatch was updated and a new reference was included
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Video rendering is fixed, GDPR and CCPA section hyperlinking is improved, and the CCPA summary is clearer
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Video rendering issues in the chapter have been resolved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: Video rendering issues in the chapter have been fixed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: Video rendering and YouTube shortened URL resolution issues were fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: The rendering of itemized lists has been fixed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 17: Sustainable AI: List item spacing was made consistent throughout the chapter and a reference to the OECD blueprint paper was added

February 02

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: Several image references were fixed, all bibtex entries were updated automatically, and the β€˜81-figure-references/part-2’ branch was merged
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Several image links were repaired, bibliographic information was corrected, and all BibTeX references were updated automatically
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Several image references were fixed, all bibtex entries were updated automatically, and figure 14.3 now renders correctly
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Several image references were fixed, grammar was corrected, and video URLs were adjusted to ensure proper rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Several image links were fixed, all BibTeX references were updated automatically, and a broken chapter link was corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Modified callout content, added a web scraping Colab exercise, updated all bibtex references automatically, and converted PNG images to JPG format
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: Redundant citation issues were fixed and all BibTeX references were updated automatically
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Reference rendering in the chapter is fixed and all BibTeX references have been updated automatically
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: A missing reference for quantization-aware pruning was added, an incomplete sparsity matrix filter illustration was removed and moved to a later section, and all bibtex references were updated automatically
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The chapter’s bullet list and formatting were updated, and a broken image reference was removed
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: SVG images were removed from the chapter and replaced with PNGs to ensure proper rendering in PDF outputs
  • β–ˆβ–‘β–‘β–‘β–‘ Embedded Sys: Bibtex references throughout the chapter were automatically updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: All BibTeX references have been updated automatically
  • β–ˆβ–‘β–‘β–‘β–‘ Embedded Ml: The image format in the chapter has been switched to PNG

January 28

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list has been updated to include all contributors

January 28

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes logos and an updated list of contributors
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 5: AI Workflow: This chapter now includes a section on data preprocessing techniques, an updated discussion on feature engineering, and a new case study on applying AI workflow to natural language processing
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: The data section now includes more citations and edits were made to later data engineering sections. Work is ongoing on a keyword section
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 8: AI Training: Added figures illustrating chip concepts, updated references to align with the hardware section, and made improvements to the training chapter content
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 19: AI for Good: The chapter includes new videos, images, updated learning objectives, and added spotlight use cases
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: Radar plots were added to Chapter 2
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Figures of chips were added and small bibliographic references were included
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Learning objectives were added, references were updated, and new figures were included
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: References were removed from the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 1: Introduction: A redundant case study was removed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 4: DNN Architectures: The chapter’s wording has been refined and corrected based on recommendations
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: Removed dead references throughout the chapter
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Pi Image Classification: Updated the code for image classification, included explanations of the model training process, and improved the clarity of the instructions
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Pi Object Detection: Updated the object detection code with explanations for TensorFlow Lite deployment on Raspberry Pi and improved code comments
πŸ“š Appendix
  • β–ˆβ–‘β–‘β–‘β–‘ PhD Survival Guide: A few favorite resources were added and one link was updated

January 17

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ SocratiQ: Updated SocratiQ interface descriptions, added examples of its use for concept mapping, and improved explanations of its learning algorithm
  • β–ˆβ–ˆβ–‘β–‘β–‘ About: The acknowledgements section was updated to include information about open-source contributions
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a list of contributors
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 3: DL Primer: A new section on generative adversarial networks (GANs) was added, along with updated examples and improved explanations of their training process
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 7: AI Frameworks: This chapter now includes an overview of AI frameworks, updated learning objectives, and a section on the history of these frameworks
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction has been revised to reflect Bravo’s feedback
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: A footnote was removed and a clarification about parameter storage bounds for RNNs was added. The table format was also updated to reStructuredText with footnotes
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Incorporated feedback provided by Bravo
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 2: ML Systems: The merge resolved issues and improved PDF rendering
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 12: Benchmarking AI: A reference issue was fixed
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Pi Vision Language Models: The code for VLM training was updated and explanations of hyperparameter tuning were added
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Large Language Models: Copyediting errors were corrected

January 12

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list was updated and PDF rendering was improved
πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction chapter now correctly renders triple quotes in PDFs and has adjusted section headers to improve readability
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: A definition for hybrid ML was added and PDF rendering was improved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Zishen made fixes to improve PDF rendering
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Updated figure sizes and revised the data labeling section with additions from Zishen and other contributors

January 11

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list has been updated to include all contributors and correct any omissions
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 2: ML Systems: A decision playbook framework was added and definitions were updated for each section of the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 5: AI Workflow: A grammar fix request was removed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: Incorporated Bravo’s suggested corrections and improvements

January 11

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ About: The book’s target audience and acknowledgements were updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list has been updated to include all contributors and correct any omissions
  • β–ˆβ–‘β–‘β–‘β–‘ SocratiQ: The SocratiQ file has been edited
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: The chapter now includes additional references, updated information on synthetic data and crowdsourcing, revised web scraping content, a refreshed problem definition, and an updated overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Footnotes have been added to provide additional context and information within the introduction

January 09

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list has been updated to include all contributors and correct any omissions
πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction has been revised based on Marco’s feedback
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Incorporated feedback from Bravo to refine the explanations of the AI workflow
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: Feedback clarity and Bravo’s output format were improved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The chapter now includes incorporated feedback from Bravo and has improved explanations
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: Incorporated feedback from Bravo and improved explanations within the chapter
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: Grammar pass fix requests were removed
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: Grammar pass fix requests were removed

January 07

πŸ“„ Frontmatter
  • β–ˆβ–‘β–‘β–‘β–‘ Foreword: The wording in the foreword has been slightly refined
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a list of contributors
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 3: DL Primer: The chapter now includes an updated figure caption, additional images and code to clarify the training loop and inference process, and a corrected typo in an equation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The distinction between artificial intelligence (AI) and machine learning (ML) is now more clearly defined
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: The chapter now includes new visualization figures and updated text based on Zishen’s feedback

January 03

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The contributor list has been updated to include all contributors and correct any omissions
  • β–ˆβ–‘β–‘β–‘β–‘ SocratiQ: Corrected several typos and inconsistencies within the SocratiQ chapter text
πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: Definitions of supervised and unsupervised learning were clarified and examples were updated for improved comprehension
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The explanation of data parallelism was corrected and the discussion on model serving was updated to reflect recent advancements
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 4: DNN Architectures: Fixed various issues within the chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Fixed a bug in the data cleaning section and updated Apache Spark code examples
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: Fixes were applied to the conclusion chapter

January 02

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a complete and updated list of contributors
πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 4: DNN Architectures: Removed unnecessary commented text and implemented suggested edits
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: Incorporated Bravo’s suggested revisions throughout the conclusion
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter: Generative Ai: Dead commented-out text has been removed from the chapter

January 01

πŸ“„ Frontmatter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Foreword: The foreword now has a smoother flow, corrected sidebar formatting issues, and includes updated text content
  • β–ˆβ–ˆβ–‘β–‘β–‘ About: The chapter order was updated and incorporated feedback from Bravo
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: The chapter’s web formatting was fixed and its content was reorganized
  • β–ˆβ–‘β–‘β–‘β–‘ Index: The abstract was updated
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes contributors and the readme has been updated to reflect this
πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–ˆβ–‘ Chapter: Dl Architectures: The chapter was renamed and rewritten with an emphasis on ML systems, incorporating Colab notebooks for interactive learning
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 2: ML Systems: The chapter now includes a Mobile ML section, improved connections with text in figures, and an added example system to ground concepts
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 4: DNN Architectures: The chapter now includes a section on transformer architectures, the RNN conclusion has been updated, and tables have been corrected for formatting and referencing
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 18: Robust AI: The chapter now includes clearer explanations of gradient norms and Bayesian Neural Networks, reframes the introduction to faults, and focuses on ML-specific fault examples in edge cases
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ About: The About chapter has been reorganized, includes Bloom’s Taxonomy, and its outline was updated to reflect the addition of Chapter 4
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The file path was fixed, header formats were updated, and Bravo’s feedback was incorporated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The file structure was reorganized, the chapter’s purpose was updated, and a giscus comment issue was resolved
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The first draft of the AI workflow content was created and the overview, along with the purpose statement, were updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The purpose of AI training and the explanation of training objectives were clarified
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The purpose of on-device learning has been clarified
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: A duplicate case study was removed from the chapter, a duplicate section was moved to Chapter 14, and the chapter’s purpose was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The chapter’s purpose was updated and incorporated feedback from Bravo
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes logos and an updated list of contributors
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: The SocratiQ chapter has been reorganized, broken links have been repaired, typos corrected, and an issue brought up by Bravo has been resolved
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: The purpose of the chapter was updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: The purpose statement for Chapter 7 has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 9: Efficient AI: The purpose statement for the chapter has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: The purpose statement for Chapter 10 has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 11: AI Acceleration: The purpose of Chapter 11 has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 12: Benchmarking AI: The purpose statement for the chapter has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 13: ML Operations: The purpose of Chapter 13 has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 16: Responsible AI: The purpose of Chapter 16 has been updated
  • β–‘β–‘β–‘β–ˆ Chapter 19: AI for Good: The chapter’s purpose has been updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: The conclusion received some wording refinements and now includes a reference to Chapter 4
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Raspi: The lab now includes a new VLM lab and the grid table formatting has been updated
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Pi Vision Language Models: A new lab exploring Vision Language Models (VLMs) has been added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs Overview: Added VLM to the main table of labs

πŸ“… 2024

November 19

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: The text was updated and an AI podcast was added
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a list of contributors

November 19

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 15: Security & Privacy: Machine unlearning was added to the chapter, a table was reordered, and a new federated learning case study replaced a previously discussed one
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The chapter’s figure placement was refined, formatting was improved, policies were summarized, and a figure was corrected with a clearer explanation
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The chapter now includes improved grammar, a new image illustrating the water footprint of AI, and an updated figure for Life Cycle Assessment
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The chapter now includes grammatical corrections and a discussion motivating the use of TinyML
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: Added .png support for gif images in PDF builds, updated the widget suggestions blog, and changed the variable name widget_access to socratiq
  • β–ˆβ–‘β–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes a list of contributors

November 16

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The explanation of a table has been improved for better clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The acknowledgements section now includes contributors and the preface material has been reorganized
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 1: Introduction: A broken reference link was fixed
  • β–ˆβ–‘β–‘β–‘β–‘ About: The file’s content was reorganized and a relative path was corrected

November 15

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 13: ML Operations: The chapter now features a more cohesive structure with grouped topics, removal of repeated content, clearer connections between roles, and a streamlined data management section
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The Introduction section has been replaced with an Overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The roles sections within Chapter 5 have been interconnected for a more cohesive flow
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The Introduction section has been replaced with an Overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The chapter now features improved definitions and an overview section replacing the introduction
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 1: Introduction: Fixed definition formatting to be normal font and addressed style consistency errors
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 3: DL Primer: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 9: Efficient AI: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: The introduction section was replaced with an overview
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 11: AI Acceleration: The introduction section was replaced with an overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: The Introduction section was replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 18: Robust AI: The Introduction section was replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 15: Security & Privacy: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 20: Conclusion: The Introduction section has been replaced with an Overview section
  • β–‘β–‘β–‘ Chapter 12: Benchmarking AI: The Introduction section has been replaced with an Overview
  • β–‘β–‘β–‘ Chapter 17: Sustainable AI: The Introduction section was replaced with an Overview section
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Setup: The Introduction section has been replaced with an Overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Motion Classification: The introduction section has been replaced with an overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspberry Pi Setup: The Introduction section has been replaced with an Overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Dsp Spectral Features Block: The introduction section has been replaced with an overview and the language has been simplified for improved readability
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: The Introduction section was replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Object Detection: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Keyword Spotting: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Setup: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Image Classification: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Object Detection: The Introduction section was replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Keyword Spotting: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Motion Classification: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Image Classification: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Object Detection: The Introduction section has been replaced with an Overview
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Pi Large Language Models: The Introduction section has been replaced with an Overview section
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Kws Feature Eng: The Introduction section was replaced with an Overview section

November 15

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 1: Introduction: The definition of machine learning was updated, case studies were added with video and image links, and the definition of AI engineering was refined
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 12: Benchmarking AI: The chapter now lacks a labs section, features reworked examples, and includes a new section discussing energy considerations within the context of benchmarking
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 15: Security & Privacy: Added labs to the chapter, updated the security content, and renamed images to enhance privacy and security
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 3: DL Primer: The DL Primer chapter was updated with new content and labs and core folders were created
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 2: ML Systems: The chapter now includes labs and a core folder, features updated ML systems content, revised learning objectives, and an introduction that encompasses a broader scope than just embedded systems
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 2: ML Systems: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder, while the core content is now in a β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: Labs have been removed from the chapters and placed in a dedicated β€œlabs” folder, while the core content is now organized in a β€œcore” folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: Labs were removed from the chapter content and moved to a new β€˜labs’ folder, while a reference was added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The lab exercises have been moved to a new β€˜labs’ folder within the existing β€˜core’ folder structure
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The labs portion has been removed from the chapters and moved into a dedicated β€œlabs” folder within the β€œcore” folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The ML Operations chapter now has a dedicated β€˜labs’ folder for practical exercises and incorporates feedback from Bravo
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The chapter content now focuses solely on theoretical concepts and explanations, removing the lab sections. Pruning is defined and discussed within the framework of on-device learning
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The chapter now excludes lab exercises and has been reorganized into β€œlabs” and β€œcore” folders
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The lab portion has been removed from the Responsible AI chapter and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The labs portion has been removed from the chapters and moved into a dedicated β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The labs portion has been removed from the chapters and moved into a new β€˜labs’ folder within the β€˜core’ folder
  • β–ˆβ–ˆβ–‘β–‘β–‘ Acknowledgements: The β€˜acknowledgements’ chapter now has dedicated β€˜labs’ and β€˜core’ folders
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: A draft of the SocratiQ bot has been created
  • β–ˆβ–ˆβ–‘β–‘β–‘ SocratiQ: A draft of the SocratiQ bot and its QMD file have been created
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: A labs folder was created and the AI4Good content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: A labs folder was created and the robustAI content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: A labs folder was created and the sustainable AI content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: A labs folder was created and the responsibleAI content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The ML Operations chapter now includes a labs and core folder structure and updated content
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The textbook now includes dedicated labs and core folders, and the on-device learning content has been updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Labs and core folders were created and the benchmarking content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: Labs and AI hardware content were added to the chapter
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: Labs and core folders were created, the β€˜dev’ branch was merged, suggested fixes were implemented, and the optimization content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: Added labs and core folders and updated the efficiency content
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: A labs folder was created and the training content was updated
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The AI Frameworks chapter now includes dedicated labs and core folders, along with updated information on various machine learning frameworks
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: The chapter now includes labs and a core folder, with updated data engineering content and an updated path
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The AI Workflow chapter now includes dedicated labs and core folders, with an updated workflow overview
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 1: Introduction: The introduction was updated with revised text and writing corrections, and new folders for labs and core content were created
πŸ§‘β€πŸ’» Labs
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Lab: Arduino Keyword Spotting: Fixed code examples, improved keyword spotting model accuracy, and added explanations for the model training process
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs: The lab content was restructured, documentation was improved, and the icon usage was adjusted to support PDF builds
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Raspberry Pi Setup: The lab now includes notes on LLMs and other generic issues, incorporates Raspberry Pi support, and uses consistent formatting for emphasis
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Image Classification: The lab now includes notes on LLMs and addresses other general issues, integrates Raspberry Pi support, and corrects the use of asterisks
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Object Detection: Fixed the output format for object detection results and improved code comments for better understanding
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Pi Large Language Models: A lab focused on Small Language Models has been added
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Labs Overview: The lab overview has been restructured to address issues related to PART
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Nicla Vision: Corrected the use of colons in code examples for consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Xiao Esp32S3: Corrected the use of colons and asterisks in text elements for consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Setup: Corrected the use of colons and asterisks in text elements for consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: XIAO Keyword Spotting: Corrected the use of colons in code examples for consistency
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Raspi: Corrected punctuation in code examples and updated the content within the raspi.qmd file

January 02

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Niclav Sys: A typo was fixed in the Installing the OpenMV IDE section
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: The chapter content now includes corrections to a callout-tip and minor syntax errors

December 19

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: Figures were added to the chapter and formatting issues along with broken references were corrected

December 18

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The chapter’s content was moved to the benchmarks/leaderboards section and a problem with reference separators was corrected
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: Content related to sustainable AI was moved to the benchmarks/leaderboards section, wording about power draw was corrected, and the chapter was proofread
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: Resolved a markdown formatting issue that affected Windows users

December 13

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The Colab notebooks for framework examples were updated

December 13

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 9: Efficient AI: A broken URL link was fixed

December 12

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 12: Benchmarking AI: Reference spacing in the chapter has been fixed

December 12

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: The file path for this chapter was updated
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: A missing reference for an attention paper was added

December 12

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: References now use square brackets instead of other formatting

December 11

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The DL primer no longer includes an activation function and its computation graph has been moved to the training section
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The DL primer activation function was removed and the computation graph was moved to the training section
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: Several definitions were updated and a few examples were added
  • β–ˆβ–‘β–‘β–‘β–‘ Generative Ai: Content in the chapter has been cleaned up
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 18: Robust AI: Text in the chapter has been cleaned up
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: Various words were changed for clarity and precision
  • β–ˆβ–‘β–‘β–‘β–‘ Embedded Ml: Various words were changed for clarity and precision
  • β–ˆβ–‘β–‘β–‘β–‘ Embedded Sys: Various words were changed for clarity and precision
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 11: AI Acceleration: Several words were changed for clarity and accuracy
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 14: On-Device Learning: Several words were changed for clarity and precision

December 11

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 12: Benchmarking AI: The text now uses β€œTinyML” consistently throughout instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 6: Data Engineering: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Embedded Sys: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 7: AI Frameworks: The text now uses β€œTinyML” consistently throughout instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 11: AI Acceleration: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Lab: Arduino Image Classification: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Kws Nicla: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 10: Model Optimizations: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 16: Responsible AI: The text now consistently uses β€œTinyML” instead of β€œtinyML”
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 5: AI Workflow: The text now consistently uses β€œTinyML” instead of β€œtinyML”

December 11

πŸ“– Chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: References to datasets and ResNet architectures were added to the chapter, and a system for distributing references by chapter was implemented
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: A broken URL was fixed and references were distributed to each chapter’s own file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The chapter’s terminology was updated for consistency, duplicate text about the lottery ticket hypothesis was removed, and references were moved to individual chapter files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The chapter now includes references for machine learning and reinforcement learning applications in architecture design space exploration, general algorithm optimization, chip floorplanning, and logic synthesis
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The AI for Good chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: References are now distributed to individual chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 6: Data Engineering: Each chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: Each chapter now has its own references file, allowing for more specific and targeted citations
  • β–ˆβ–ˆβ–‘β–‘β–‘ Dsp Spectral Features Block: Distributed references so each chapter has its own references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Ml: Distributed references to individual chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Embedded Sys: Distributed references to individual chapters
  • β–ˆβ–ˆβ–‘β–‘β–‘ Generative Ai: The Generative AI chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: Each chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Kws Feature Eng: References are now distributed to individual chapter files
  • β–ˆβ–ˆβ–‘β–‘β–‘ Kws Nicla: The Kws Nicla chapter now has a dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Motion Classify Ad: The Motion Classify Ad chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Niclav Sys: The Niclav Sys chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Object Detection Fomo: The Object Detection Fomo chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: Each chapter now has its own references file to improve organization and clarity
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: Distributed references so each chapter has its own references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: Each chapter now has its own references file and the book was updated with changes from the β€˜upstream/main’ branch
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The Responsible AI chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: The Robust AI chapter now has its own dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The Sustainable AI chapter now has a dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The AI Training chapter now has a dedicated references file
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The workflow chapter now has its own dedicated references file

December 10

πŸ“– Chapters
  • β–ˆβ–‘β–‘β–‘β–‘ Chapter 8: AI Training: References now consistently appear before periods

December 10

πŸ“– Chapters
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Chapter 6: Data Engineering: The images folder was reorganized with subfolders by file type and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Dsp Spectral Features Block: The images folder was reorganized with subfolders based on filetype and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Embedded Ml: The image directory has been reorganized with subfolders by file type and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Embedded Sys: The image directory was reorganized with subfolders based on file type and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Generative Ai: The image directory was reorganized with subfolders by file type and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Motion Classify Ad: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–ˆβ–‘β–‘ Niclav Sys: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 19: AI for Good: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 12: Benchmarking AI: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a more organized folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 3: DL Primer: The image directory has been reorganized with subfolders based on file type, and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 9: Efficient AI: The image directory was reorganized with subfolders by file type and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 7: AI Frameworks: The image directory has been reorganized with subfolders by file type and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 11: AI Acceleration: The image directory has been reorganized with subfolders based on file type, and all files have been restructured into a more organized folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Lab: Arduino Image Classification: The image classification lab now has subfolders within the images/ directory based on file type and all files have been reorganized into a more structured folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Kws Feature Eng: The images folder was reorganized with subfolders based on file type, and all files were restructured into a more organized folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Kws Nicla: The images folder was reorganized with subfolders based on file type and all files were reorganized into a more structured folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Object Detection Fomo: The image directory was reorganized with subfolders based on file type and all files were restructured into a more organized folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 14: On-Device Learning: The images folder was reorganized with subfolders based on file type and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 13: ML Operations: The images folder was reorganized with subfolders based on file type and all files were restructured into a more organized folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 10: Model Optimizations: The image directory has been reorganized with subfolders based on file type and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 15: Security & Privacy: The image folder has been reorganized with subfolders based on filetype and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 16: Responsible AI: The image folder has been reorganized with subfolders based on filetype and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 17: Sustainable AI: The image directory has been reorganized with subfolders based on file type, and all files have been restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 8: AI Training: The images folder is now organized by file type and all files have been reorganized into a new folder structure
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 5: AI Workflow: The images folder was reorganized with subfolders based on file type, and all files were restructured into a new folder system
  • β–ˆβ–ˆβ–‘β–‘β–‘ Chapter 18: Robust AI: The files have been reorganized into a folder structure
Back to top