Skip to content

Latest commit

 

History

History
9 lines (5 loc) · 662 Bytes

README.md

File metadata and controls

9 lines (5 loc) · 662 Bytes

This repository contains implementations of fundamental machine learning algorithms developed from scratch. The key features of the codebase include:

  1. Comprehensive inline comments to enhance readability and understanding.
  2. Implementation of custom loss functions, optimizers, dataset preparation, training mechanisms.
  3. Optimization for execution on "mps" GPU using PyTorch, enabling seamless operation on devices such as MacBooks equipped with M1 chips. For users employing a "cuda" device, appropriate modifications to the device settings are required.
  4. Proper initialization of model parameters to ensure effective and stable training.