AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
AI Trends 2023: Causality and the Impact on Large Language Models with Robert Osazuwa Ness - #616
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is There a Loss Function That You Can Use to Optimize the Intervention?
The more correct your graph is, the less effect given intervention will have on nodes in the graph that aren't downstream of where the intervention occurs. So they then somehow translate the degree to the intervention impacts these other states into some kind of loss function and then kind of optimize across that. This is the first time I've seen one where the interventions are unknown. And so I would say like this one is seamlessly integrated into a loss function that you would optimize in a unsupervised training procedure.
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