Implementing Neural Networks with Pure NumPy: Understanding Core Deep Learning Principles from Scratch

Introduction / Main Floor: Implementing Neural Networks with Pure NumPy: Understanding Core Deep Learning Principles from Scratch

This project demonstrates how to build a complete neural network from scratch using only NumPy, including forward propagation, backpropagation, and optimizers. It achieves an 84% test accuracy on the Fashion MNIST dataset, making it an excellent learning resource for understanding the underlying principles of deep learning.