Historical Milestones
Proof-of-Mastery Demonstrations | 6 Milestones | Prerequisites: Vary by milestone
Milestones are runnable recreations of historical ML breakthroughs that use YOUR TinyTorch implementations. Each one validates that the components you built across the modules can reproduce results that once made headlines.
Overview
You’ve spent the modules building a working ML framework — tensors, autograd, layers, optimizers, attention. The milestones answer the only question that matters: does it actually run the experiments that defined the field?
You’ll find out by rebuilding history. Each milestone reproduces a landmark result — Rosenblatt’s Perceptron, the XOR crisis, backpropagation, convolutional networks, transformers, MLPerf — using your code. When the Perceptron computes its first predictions, it’s running your tensor, layer, and activation stack. When attention processes a sequence, it’s running your multi-head attention on top of your transformer block. When a CNN recognizes TinyDigits, those are your convolutional layers extracting the features.
That makes these chapters proof — to yourself, and to anyone reading your repo — that the framework you built is the same kind of artifact the original papers shipped on.
The Journey
Table 1 traces the historical milestone timeline and the modules each one requires.
| Year | Milestone | What You’ll Build | Required Modules |
|---|---|---|---|
| 1958 | Perceptron | First neural network forward pass | 01–03 |
| 1969 | XOR Crisis | Experience the AI Winter trigger | 01–03 |
| 1986 | MLP Revival | Backprop solves XOR + digit recognition | 01–08 |
| 1998 | CNN Revolution | TinyDigits CNN, with optional CIFAR-10 scale-up | 01–09 |
| 2017 | Transformers | Multi-head attention on structured sequence tasks | 01–08, 11–13 |
| 2018 | MLPerf | Production optimization pipeline | 01–08, 14–19 |
Why Milestones Transform Learning
You’ll feel the historical struggle. When your single-layer perceptron hits 50% accuracy on XOR and refuses to budge — loss stuck at 0.69, epoch after epoch — you’ll understand in your bones why Minsky’s proof stalled neural-network research for a decade. The AI Winter wasn’t abstract skepticism; it was researchers watching their perceptrons fail in exactly the way yours just did.
You’ll experience the breakthrough. Then you add one hidden layer. Same data, same training loop. Suddenly: 100% accuracy. Loss collapses to zero. You didn’t just read about how depth unlocks non-linear representations — you watched your two-layer network solve what your one-layer network couldn’t. That’s lived experience, not summary.
You’ll build something real. By Milestone 04 you’re done with toy demos. You’re training a LeNet-style CNN on TinyDigits, extracting spatial features with your convolutional layers, and optionally scaling the same code path to CIFAR-10 — using a network you wrote line by line, on a framework you wrote module by module.
How to Use Milestones
tito module status
tito milestone run 01
cd milestones/01_1958_perceptron
python 01_rosenblatt_forward.pyEach tinytorch/milestones/NN_yyyy_name/ folder contains:
README.md— full historical context and instructions- Python scripts — runnable demonstrations for each milestone part
Learning Philosophy
Module teaches: HOW to build the component
Milestone proves: WHAT you can build with itModules give you the parts. Milestones force the parts to do real work — the same work that, in each case, moved the field forward.
What’s Next?
Start at the beginning. Open milestones/01_1958_perceptron/, run 01_rosenblatt_forward.py, and watch a single-layer network — built on your tensor, Linear, and Sigmoid implementations — compute real predictions before any training infrastructure exists. From there the path is chronological: each milestone exposes the next constraint, then later milestones introduce the ideas that broke through it.
Build the future by understanding the past.