Lecture Slides — Fall 2026

One deck per session. Course home · Syllabus

Module 1 — Foundations

S01	Course Introduction
S02	From Linear Models to MLPs
S03	Loss Functions and Gradient Descent
S04	Backpropagation IHW1 out
S05	Backpropagation II & Autograd
S06	Optimizers
S07	Regularization, Initialization, Normalization
S08	PyTorch in PracticeHW1 due

Module 2 — CNNs & Training Practice

S09	CNNs IQuiz 1
S10	CNNs II: ResNet & Modern Design
S11	Transfer Learning & AugmentationProject guide out
S12	Training in PracticeHW2 outMidterm Exam Week

Module 3 — Sequences, Transformers & LLMs

S13	RNNs and LSTMsQuiz 2Midterm Exam Week
S14	Attention
S15	Guided Review · review guideNot held this term · for self-study
S16	Transformer I
S17	Transformer II
S18	LLM Pretraining & ScalingHW2 due · HW3 out
S19	Fine-Tuning & LoRA
S20	Decoding, Prompting, In-Context LearningOne class with S21
S21	Alignment: SFT, RLHF, DPOOne class with S20
S22	ViT & MultimodalHW3 due

Module 4 — Generative Models, Efficiency & Evaluation

S23	Autoencoders & VAEsQuiz 3
S24	GANs
S25	Diffusion Models
S26	Efficiency & ScaleHW4 out
S27	Evaluation & SafetyQuiz 4

Finale

S28	Code Defenses I
S29	Code Defenses II + Wrap-UpHW4 due