AI explainability

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Apr 3, 2023 by Sarah Catanzaro · across every show →

Everything said about AI explainability, oldest first

Apr 3, 2023
Insight
Catanzaro: AI research must detect model failures before solving explainability
“Perhaps we need to solve the first problem first, which is just understanding when models are not performing, or like when there are errors or failure cases before we can understand why.”
Sarah Catanzaro Apr 3, 2023 ▶ 35:10 A Conversation with Sarah Catanzaro, Amplify Partners
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.