Fundamentals of Deep Learning

Mathematical and conceptual introduction to Deep Learning: basic concepts, model classes, paradigms, and attempts at analysis. Covers some ML theory (learning rate, SGD, generalization, etc.) and then some advanced topics: Normalization, Implicit Bias, Generative Models, Recurrent Nets, Contrastive Learning, Self-Supervised Learning, Transformers, Diffusion Models, Private Learning, Interpretability, Fine-tuning of Large Pretrained Models, etc. (Varies year to year.) 4 home-works. Term project done in groups of 2-3 --- can be experimental or theoretical. Course text available from Instructor's homepage.