Machine Learning
Prepare for the AI era
-
ML Foundations
Start here. Nearest neighbors, linear models, optimization, SVMs, trees, and the math behind them. No prerequisites.
After ML Foundations
Deep Learning
Backprop, optimization, normalization, CNNs, sequence models, and an intro to attention. Assumes ML Foundations.
After ML Foundations
Applied ML & Evaluation
Metrics and calibration, data leakage, interpretability, and monitoring models in production.
After ML Foundations
Reinforcement Learning
MDPs and value functions, dynamic programming, model-free methods, and policy gradients.
After Applied ML & Evaluation
ML in Other Domains
NLP, computer vision, recommender systems, and graph ML.
After ML in Other Domains
ML Systems & Inference
Attention internals, the KV cache, inference performance, quantization, parallelism, GPU/TPU kernels, and JAX.
After ML in Other Domains
Advanced ML
Learning theory, gradient boosting internals, uncertainty, self-supervised learning, generative models, and causal inference. Assumes Foundations and Deep Learning.