Implementation of the Minitorch library for the Machine Learning Engineering course at Cornell University.
Minitorch is a diy teaching library for machine learning engineers who wish to learn about the internal concepts underlying deep learning systems. 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.
- module: ML Programming Foundations
- module: Autodifferentiation
- module: Tensors
- module: GPUs and Parallel Programming
- module: Foundational Deep Learning