TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

The Annotated S4

111 pointsby profchemaiover 1 year ago

4 comments

srushover 1 year ago
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: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;dKJEpOtVgXc?si=PDNO0B0qi6ARHaeb" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;dKJEpOtVgXc?si=PDNO0B0qi6ARHaeb</a><p>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).
评论 #39350168 未加载
评论 #39349379 未加载
imjonseover 1 year ago
A lot of intimidating math that will make all self-attention tutorials seem like a walk in the park in comparison. Luckily subsequent state space models building on S4 (DSS, S4D and newer ones like Mamba) simplified the primitives and the math used.
评论 #39348264 未加载
评论 #39351713 未加载
评论 #39350537 未加载
medvover 1 year ago
What I need so learn to start to understand those articles? Is there some good courses on the topic? For beginners?
adamnemecekover 1 year ago
All machine learning is convolution.