AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
ICLR 2020: Yann LeCun and Energy-Based Models
Machine Learning Street Talk (MLST)
Inference Time Energy Minimization
No model in this entire talk does this actively at inference time. So even though, again, the generator learns to minimize the energy function during training, when it produces a sample, it doesn't actually optimize the energy function. And maybe this reasoning through vector representations and energy minimization is allusion to the fact that if we had an energy function, they tell us what are logical things. I imaginive classifier of what water, what statements are logical and what statements are illogical.
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