#interpretable — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #interpretable, aggregated by home.social.
-
Weight-sparse transformers have interpretable circuits [pdf]
https://cdn.openai.com/pdf/41df8f28-d4ef-43e9-aed2-823f9393e470/circuit-sparsity-paper.pdf
#HackerNews #Weight-sparse #transformers #interpretable #circuits #AI #research #machine #learning #pdf
-
Interview of #CynthiaRudin about #InterpretableML. She is advocating #interpretable models for high-stake #decisions, which merit the extra training effort. Those #whiteboxes (or should we say #lightboxes?) give us hope in times where business leaders feel tempted to surrender to obscure #darkboxes (sounds more adequate than #blackboxes, doesn’t it?), which escape #accountability and #adjustability!
“Cynthia Rudin Builds AI That Humans Can Understand” | Quanta Magazine