AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Been Kim: Interpretable Machine Learning
The Gradient: Perspectives on AI
Towards a Rigid Science of Interpretability
The paper suggests three different levels of testing. The golden standard is to test with actual experts and the users, it says. It's like real humans, real tasks, real humans simplify tasks, and then no humans in proxy tasks. But you can test with bigger pool of people, maybe turkers, maybe your co co student grad students or others,. You can sort of go through this levels, but at the end to evaluate your method...
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode