Homemade chess board moves its own pieces. And wins.

To move its own pieces, a motorized mechanism beneath the board guides an electromagnet along the underside. When activated, ...
GitHub

A Two-Phase Reinforcement Learning Chess Engine

Combining supervised pretraining on master-level games with AlphaZero-style self-play reinforcement learning, using a SE-ResNet architecture with spatial attention and Win/Draw/Loss value estimation.
IEEE

Bayesian Neural Networks via MCMC: A Python-Based Tutorial

Abstract: Bayesian inference provides a methodology for parameter estimation and uncertainty quantification in machine learning and deep learning methods. Variational inference and Markov Chain ...
GitHub

Chess AI Training Pipeline

A comprehensive Python-based training pipeline for fine-tuning chess AI models with Azure AI Foundry. This project processes chess game databases, converts them to coordinate notation format, and fine ...