AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min snip
Been Kim: Interpretable Machine Learning
The Gradient: Perspectives on AI
The Difficulty of Causal Inference
The difficulty in both the generative model work and the causal work is the following. It comes with a lot of a af extra things that you need to do. So we e rote paper on concept bottle neck models. This is er in presilion, where we insert those conon concepts that we want to be able to have access to an estimate importance of in the middle of the network. Then i can zero out than neuron and en en for four feet forward and get a new prediction. And we show pretty inactually medical data in the paper, that this control ability improves the accuracy too. But i like the wayt you talked about how different in in inductive biases, and
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