Description
CS224N is Stanford's course on natural language processing with deep learning, taught in Winter 2026 by Diyi Yang and Yejin Choi. It starts with word vectors, neural networks and backpropagation, then moves through language models, transformers and self-attention, pretraining, post-training, prompting and parameter-efficient fine-tuning. The current schedule also covers agents, tool use and retrieval-augmented generation, benchmarking and evaluation, reasoning and interpretability. Slides, notes and assignments are posted on the course site, and lecture videos from the 2024 offering are free on YouTube. A solid path for developers who know Python and basic machine learning and want a structured route from embeddings to modern LLM practice.
