How machines read and write. Covers tokenization, word vectors, attention, and the transformer architecture that powers today's language models, plus hands-on work with Hugging Face.
Sorted cheapest first. Click a column header to re-sort. Developers and linguists with Python basics.
| Course | Level | Duration | Price | Certificate | |
|---|---|---|---|---|---|
Stanford University |
advanced | 10 weeks (one quarter) | Free | No | Visit |
DeepLearning.AI · Coursera |
intermediate | 3 months at 10 hrs/week (4 courses) | Free to audit Free to audit · $49/mo |
Yes | Visit |
Stanford University · Stanford Online |
advanced | 10 weeks at 10-15 hrs/week | Paid $1,950 |
Yes | Visit |
No payment required. Several of these are complete university courses.
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.
Watch everything free; pay only if you want graded assignments and a credential.
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.
Structured programs with instructors, cohorts, projects or formal credentials.
The professional version of CS224N with graded coding assignments, facilitated discussion, and a Stanford record of completion. Choose it when you want accountability and credentialing on top of the free lecture material.
Transformers, large language models, fine-tuning, and building with foundation models.