Download
ai-notebooks is a collection of Jupyter notebooks that implements machine-learning and artificial-intelligence ideas in compact, inspectable experiments. The examples are written primarily in Python and use frameworks including TensorFlow, PyTorch, Keras, JAX, and tinygrad. Projects explore problems such as MNIST learning, GANs, VAEs, model compression, and knowledge distillation. Other notebooks examine reinforcement learning through PPO, SAC, TD3, VPG, and MuZero experiments. Transformer, recurrent-network, counterfactual-regret, and normalizing-flow examples broaden the collection. The notebooks are designed to be read directly on GitHub, making the repository useful for studying algorithms through working code.
Features
- Jupyter-based machine-learning experiments
- TensorFlow, PyTorch, Keras, and JAX examples
- GAN, VAE, and model-compression experiments
- PPO, SAC, TD3, and VPG reinforcement learning
- MuZero and game-learning implementations
- Transformer and recurrent-network examples
Project Samples
