A framework for mini neural networks (perceptrons), written from scratch in python. The goal of the project is to demystify the workings of a neural network and various training algorithms by providing code written from scratch for the simplest neural network one could have.
An Educational Framework Based on PyTorch for Deep Learning Education and Exploration
Use LLMs as training regularizers for small, differentiable models and significantly improve their generalization ability when trained on few-shot and skewed datasets.
My take on PFN Internship ML Task 2019
♟️ Optimized Chess RL Trainer using DQN vs Stockfish. Built with PyTorch and python-chess, it learns using per-move rewards from Stockfish evaluations. Implements Prioritized Experience Replay (PER) and parallel CPU/GPU execution for faster training. The agent dynamically adjusts Stockfish skill level based on performance.
Add a description, image, and links to the training-algorithms topic page so that developers can more easily learn about it.
To associate your repository with the training-algorithms topic, visit your repo's landing page and select "manage topics."