HackerTube.runGood videos, with context.
Do we need Attention? - Linear RNNs and State Space Models (SSMs) for NLP
About this video
Sasha Rush surveys linear RNNs and state space models as replacements for attention in transformer-style models, in a talk for MLSys. It covers the foundational preliminaries and predates Mamba.
Why it appears in the archive
HN commenters recommend it for building intuition about state space models and the tradeoffs between transformer and SSM layers.
AI-generated summary and labels from the source dataset; verify important details against the video. Source & credits.
From the Hacker News discussion
To those curious about the tradeoffs between transformer and state space model layers, I highly recommend Sasha Rush's video on it: [VIDEO]
Read original comment ↗Would recommend Sasha Rush's lecture [VIDEO] , it provides the intuition for state space models via linear RNNs
Read original comment ↗Hi! Blog author. This was an attempt a couple years ago to understand and write about this paper in a detailed way. Here is a video going through this topic as well: [VIDEO] Section 2 of the blog post is no longer very relevant. A lot of advances (DSS, S4D) simplified that part of the process. Arguably also this all should be updated for Mamba (same authors).
Read original comment ↗