Skip to content

Instantly share code, notes, and snippets.

@CarloNicolini

CarloNicolini/talk_padova.md

Last active November 7, 2023 10:42
Show Gist options
  • Save CarloNicolini/46d1579e420a10c2ffd932eb5707f108 to your computer and use it in GitHub Desktop.
Save CarloNicolini/46d1579e420a10c2ffd932eb5707f108 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
talk_padova.md

Visualization of self-attention maps in vision

https://epfml.github.io/attention-cnn

BertViz: Visualization of attention in NLP models

https://github.com/jessevig/bertviz

Visualization of RNNs

https://distill.pub/2019/memorization-in-rnns

Peter Bloem blog on Transformers

https://peterbloem.nl/blog/transformers

Harvard NLP on Transformers

https://nlp.seas.harvard.edu/2018/04/03/attention.html

Explained Transformers

https://e2eml.school/transformers.html

Loss landscapes artistic visualization

https://losslandscape.com/

Dylan Patek blog on semiconductors industry and AI

https://semianalysis.com

ArsTechnica on the latest interpretability attempts for LLMs

https://arstechnica.com/science/2023/07/a-jargon-free-explanation-of-how-ai-large-language-models-work/

Related sources and news

Papers

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment