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)
The Challenges of Deep Learning in Machine Learning
An energy function is basically just a function that is happy when you input something that looks like data. This can be applied to almost anything you can think of. Yan lakoon presents three challenges that deep learning must solve. The first of which is learning with fewer labelled samples and or fewer trials. We've seed an obvious example of this in papers like curl or simslar. Another recent paper, reinforcing learning with augmented data, surpasses curl. With more data. Augmentation, rather than multi task, helps tupervise learning.
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