Micrograd, rebuilt
Python
The problem
Automatic differentiation can feel like a black box when a framework does all the work.
How I solved it
Rebuilding the Micrograd library from scratch to understand the underlying math and operations of a simple deep learning library. Implemented forward and backward propagation, gradient descent, and backpropagation using only pure Python Syntax.
- Rebuilt Micrograd library from scratch
- Implemented forward and backward propagation
- Created gradient descent algorithm
- Used pure Python Syntax
The results
A pure-Python implementation of forward propagation, backpropagation, and gradient descent.