Stanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 1 - Transformers

For more information about Stanford’s graduate programs, visit: https://online.stanford.edu/graduate-education

To follow along with the course schedule and syllabus, visit: https://cme295.stanford.edu/syllabus/

Chapters:
00:00:00 Welcome
00:03:43 Difference from last year’s edition
00:05:01 Class logistics
00:12:42 Timeline
00:16:56 Tokenization
00:37:27 Word2vec (CBOW, Skip-gram)
00:48:26 RNN, LSTM
00:55:18 Attention
00:57:16 Self-attention mechanism
00:59:54 Query, key, value
01:09:35 Transformer architecture
01:12:19 Input
01:16:27 Transformer Encoder
01:18:19 Transformer Decoder
01:22:16 Computational tricks
01:27:35 End-to-end example

Afshine Amidi is an Adjunct Professor at Stanford University.

Shervine Amidi is an Adjunct Professor at Stanford University.

Follow the playlist: https://youtube.com/playlist?list=PLakGfbKCei80&si=HF2tNywj7nXIQq8X