🌏 中文版
Video status: Videos included. Source details
Lecture 2 of MIT 6.S191 2026 is Sequence Modeling: From RNNs to Attention. It Addresses data where order changes meaning—text, audio, and time series—and connects directly to music generation in Lab 1. This note uses only the official 2026 slides and video; it does not mix in similarly named material from 2025.
What to take away
- Understand how recurrent state carries the past forward
- Recognize gradient and memory bottlenecks in long sequences
- Treat attention as query-dependent information selection, not a magic block
These goals have one thing in common: recognizing terminology is insufficient. You should be able to identify inputs, outputs, the learning signal, and the main constraint before moving on.
A sequence model combines the current token with prior context and predicts the next step. An RNN compresses memory into recurrent state, while attention lets each position retrieve other positions according to a query. Neither mechanism automatically understands long-range causality; longer sequences still create memory, compute, and data-quality limits.
How to watch
First scan the sections and diagrams in the official slides, then watch the official video. On a second pass, pause at equations and architecture diagrams and redraw them in your own notation. Afterward, close the material and write three central ideas plus one unresolved question.
An exercise for tonight
Take a short ABC score and manually form input/next-character pairs before opening Lab 1 Part 2.
“Finished” means leaving a checkable diagram, calculation, program output, or short note—not merely reaching the end of the video. You should also be able to explain one failure mode to someone else.
Scope and limits
6.S191 is a high-intensity introduction, and this article is only a lecture guide. It does not replace the full recording, rigorous derivations, or instructor feedback. Use a semester course or primary papers when a topic needs theoretical depth.
Course video sources
Rechecked against the live official course page on 2026-10-10: the lecture numbers and recording links match and the videos are public and embeddable.
Original videos: MIT 6.S191: Recurrent Neural Networks, Transformers, and Attention
Course and recording entries:
Checked: 2026-10-10.
Content check: verified against the video transcript (2026-10-10): the video is presented by Ava Soleimany; the transcript covers the RNN recurrent state, next-word prediction, tokenization/embedding, backpropagation through time, vanishing/exploding gradients, a mention of LSTM, music generation (the Schubert unfinished symphony, tied to Lab 1) and attention with query/key/value, matching this note.
Update Log
- 2026-10-10: Added explicit video status and checked recording sources and access notes.
- 2026-10-10: Rechecked video status. Live-checked the official course page: lecture numbers and recording links match and the videos are public, so the status is now “Videos included.”
- 2026-10-10: Checked the video content against its transcript. The topic and speaker match; nothing needed correcting.
References
Loading...