MiniTorch Module 1

MiniTorch is a teaching library for machine learning engineers who wish to learn about the internal concepts underlying deep learning systems. Specifically, it is a pure Python re-implementation of the Torch API designed to be simple, easy-to-read, tested, and incremental. The final library can run Torch code with minimal changes (at some efficiency cost). The project was developed for the course Machine Learning Engineering at Cornell Tech.

The project is organized into 5 modules. Each module is build upon the precedents.

• Module-0
• Module-1
• Module-2
• Module-3
• Module-4

This is Module-1 and it is focused on auto-differentiation and backpropagation.

Notes

• Docs: https://minitorch.github.io/

• Overview: https://minitorch.github.io/module1.html

This module requires operators.py and module.py from Module 0

cp ../Module-0/operators.py ../Module-0/module.py minitorch/

• Tests:

python run_tests.py