Deep Learning

A technical deep dive into DeepSeek’s Manifold-Constrained Hyper-Connections (mHC), exploring how Doubly Stochastic Matrices and the Birkhoff Polytope solve gradient instability while expanding network capacity.

Complete implementations of all major reinforcement learning algorithms from foundations to state-of-the-art.

Face swap model using diffusion models for realistic identity transformation with high fidelity.