AI/ML Notes#

A notebook on artificial intelligence and machine learning — concepts, intuitions, and key results organized for reference.

Topics#

• Foundations — math, probability, linear algebra, optimization
• Neural Networks — perceptrons, backprop, activations, regularization
• Training — loss functions, optimizers, learning rate schedules, batch norm
• Architectures — CNNs, RNNs, Transformers, SSMs
• NLP — tokenization, embeddings, language models, RLHF
• Computer Vision — image classification, object detection, segmentation, diffusion
• Reinforcement Learning — MDPs, policy gradients, Q-learning, PPO
• Tools & Practice — PyTorch, JAX, experiment tracking, deployment