MaximeVandegar/Papers-in-100-Lines-of-Code

Covers 59 peer-reviewed papers spanning deep learning architectures (GANs, VAEs, normalizing flows), reinforcement learning (DQN, PPO, MAML), and optimization methods, each distilled to minimal working implementations. Implementations use PyTorch with NumPy for core algorithms, prioritizing mathematical clarity and educational value over production optimization. The collection serves as a reference for understanding foundational ML concepts through concise, reproducible code examples linked directly to original papers.

2,618 stars. Actively maintained with 1 commit in the last 30 days.