CS224N: Natural Language Processing with Deep Learning
Stanford's flagship graduate NLP curriculum covering word vectors, attention, transformers, and large language model pre-training.
- Duration
- 50+ hours
- Price
- Free
- Format
- Video
- Level
- Advanced
Free
Listed price. Confirm current access and any certificate fees on the official site.
Independent listing. We do not sell this course. You leave our site and the provider's terms apply. Some links may be affiliate links. Disclosure.
Trademark and Nominative Fair Use
CS224N: Natural Language Processing with Deep Learning and Stanford Online are trademarks of their respective owners. AI Learn Grid is an independent educational directory and is not affiliated with, sponsored by, or endorsed by Stanford Online. Outbound links direct attendees to the official provider platform.
What you'll learn
- Derive Word2Vec and GloVe objective functions from scratch
- Implement multi-head self-attention and positional encodings in PyTorch
- Master fine-tuning strategies including LoRA and prefix tuning
- Evaluate language models using perplexity and downstream task benchmarks
About this course
Taught by Christopher Manning and Stanford faculty. This world-renowned course covers word vectors, recurrent neural networks, self-attention, the Transformer architecture, and pre-training paradigms like BERT and GPT. Complete lecture videos, syllabus, and PyTorch problem sets are freely available to the public.
Prerequisites
Proficiency in Python, multivariable calculus, and linear algebra