MNIST Digit Classifier
Neural network implementation from scratch with 98.32% accuracy on the MNIST handwritten digit dataset.
Overview
This project implements a neural network from scratch using only NumPy and PyTorch (for matrix operations), achieving 98.32% accuracy on the MNIST handwritten digit classification task. I built the entire network architecture including forward propagation, backpropagation, and various optimization algorithms to understand the fundamental concepts behind neural networks before using higher-level frameworks.
Key Features
- Custom implementation of backpropagation algorithm
- Multiple activation functions (ReLU, Softmax)
- Mini-batch gradient descent with momentum
- Learning rate scheduling
- Regularization techniques (ex. dropout)
Challenges & Solutions
Implementing backpropagation from scratch was challenging, especially since there's so much going on (weight initializations, dropout rates, etc.), and ensuring correct gradient computation (that was done by hand, ouch). I verified my implementation by comparing results with PyTorch's autograd on simple cases.
Status
CompletedTech Stack
Year
2024
Related Projects
Merin
An intelligent email platform reimagined for the AI era, designed to help users process emails faster with AI-powered assistance.
Obsidian Vercel
A tool for Obsidian users to avoid paying for publish/sync and host their notes on Vercel via a CI/CD pipeline.
UBC Purity Test
A fun platform that allows UBC students to test their innocence level with custom surveys for different faculties.