Stanford University
Stanford's flagship NLP course moves from word vectors and RNNs to transformers, pretraining, RLHF, and modern LLM topics with public slides and assignments. The go-to self-study syllabus for anyone who wants to understand how today's language models actually work.
Developers and linguists with Python basics. This is an advanced course in Natural Language Processing, running about 10 weeks (one quarter).
Free. Current-quarter videos are enrolled-students only; complete Spring 2024 lectures are free on Stanford Online's YouTube channel. Slides and assignments are public.
Four courses that progress from classical methods (naive Bayes, logistic regression, HMMs) through sequence models and attention-based translation and summarization. A structured, certificate-bearing path for learners who want NLP fundamentals before diving into LLM tooling.