AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
1min snip
Yann LeCun: Deep Learning, Convolutional Neural Networks, and Self-Supervised Learning
Lex Fridman Podcast
Reasoning Requires Structure for Learning
Learning is viewed as the automation of intelligence, which inherently includes reasoning as a result of the learning process. The compatibility of reasoning and learning poses a challenge, particularly in defining how reasoning can be generated from neural networks. While neural networks have the potential to facilitate reasoning, it requires careful structuring of the networks to emulate human-like reasoning through learning. Furthermore, traditional logical models of reasoning are often incompatible with advanced learning methods that rely on gradient-based information, highlighting a preference for holistic learning approaches over discrete mathematics.
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