AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
#64 Prof. Gary Marcus 3.0
Machine Learning Street Talk (MLST)
The Importance of Being Able to Recover the Parts
Ineral networks gain a lot of their power by being able to share representational states across different n i ment, i use the term loosely here, categories. If all you have is a whole, then you can wind up with weird phenomena like the sentences, john is alive and john is not alive might be closer together in space than those two sentences are to John h jellybeans a. The second thought is, how do inductive priors extrapolate at all? Where they create essentially junk over space so it becomes interprative Data augmentation does the same thing. It's creating more space for reasoning as we know it.
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