Course 1: Fundamentals of TinyML

← Back to TinyML Overview Download All (ZIP) edX Course
Chapter 1 · Course 1

Welcome to TinyML

Core concepts, challenges, and opportunities of TinyML. Overview of the specialization, introduction to responsible AI, and getting started with Google Colab and TensorFlow.

Textbook companion: Vol I Ch 1–2 · Hardware Kits

§1.1 Course Overview

Topic Type
What is this specialization all about? Slides
Who is this course aimed at (everyone)? Slides
What will you learn? Slides
How is the course structured? Slides

§1.2 The Future of ML is Tiny and Bright

Topic Type
What is (tiny) Machine Learning? Slides
TinyML application case studies Reading
How do we enable TinyML? Slides

§1.3 TinyML Challenges

Topic Type
What are the Challenges for TinyML (Part A)? Slides
What are the Challenges for TinyML (Part B)? Slides
What are the Challenges for TinyML (Part C)? Slides
What are the Challenges for TinyML (Part D)? Slides
Why the Future of ML is Tiny Reading
Introduction to Responsible AI/ML Slides
Case Studies of Responsible AI/ML Failures Reading

§1.4 Getting Started

Topic Type
What resources are needed for this course? Slides
Colab in this Course Slides
Learning Colab Colab
Tips for using Colab Reading
Sample TensorFlow code Reading
Chapter 2 · Course 1

Introduction to (Tiny) ML

The machine learning paradigm, deep learning building blocks, CNNs, computer vision, and responsible AI design. Hands-on with loss functions, gradient descent, neural networks, and image classification.

Textbook companion: Vol I Ch 3–6

§2.1 The Machine Learning Paradigm

Topic Type
The machine learning paradigm Slides
Thinking about Loss Slides
Exploring Loss Colab
Minimizing Loss Slides
Exploring Gradient Descent Colab
First Neural Network Slides
First Neural Network in Colab Colab
More on Neural Networks Reading
Machine Learning Case Studies Reading
Neural Network Coding Assignment Colab
Assignment Solution Reading

§2.2 The Building Blocks of Deep Learning

Topic Type
Initialization in Machine Learning Reading
Understanding Neurons Slides
Neurons in Action Colab
Coding Stepback Reading
Multi-Layer Neural Network Colab
Introduction to Classification Slides
Coding Exercise: DNN Colab
Training, Validation, and Test Data Slides
Realities of Coding Neural Networks Reading
Coding Assignment: DNNs Colab
Assignment Solution Reading

§2.3 Exploring Machine Learning Scenarios

Topic Type
Quick Recap Reading
Introducing Convolutions Slides
Coding Exercise: Filters Colab
From DNN to CNN Slides
Coding Exercise: CNN Colab
Mapping Features to Labels Reading
Coding Exercise: Computer Vision Colab
Coding Assignment: CNNs Colab
Assignment Solution Reading

§2.4 Building a Computer Vision Model

Topic Type
Quick Recap Reading
Preparing Image Data Slides
Coding Exercise: Complex Images Colab
TFDS for Image Data Reading
Overfitting Slides
Coding Exercise: Image Augmentation Colab
Dropout Regularization Reading
Exploring Loss Functions and Optimizers Reading
Coding Assignment: Enhancing a CNN Colab
Assignment Solution Reading

§2.5 Responsible AI Design

Topic Type
What Am I Building? What's the Goal? Slides
Development and TinyML Reading
Who Am I Building This For? Slides
What Are the Consequences for the User When It Fails? Slides
Error Types and Ethics Reading

§2.6 Course 1 Summary

Topic Type
Recapping (Tiny) ML and its Data-Centric Role Reading
Why We Are Excited About TinyML Slides
What We Have Learned Thus Far Slides
What's Coming Next Slides
Note

These materials were originally developed for the HarvardX Professional Certificate in Tiny Machine Learning on edX. See the original curriculum for the full item-by-item breakdown including forum prompts and quizzes not listed above.

Back to top