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)
Multi Task Learning
Multi task learning is helping with the problem of how to train a discriminator. The image domain is just so prone to adversarial examples that you don't know when to stop the generator. Every time tha degenerator produces one, it will be like no to to top dop and if you just keep the criminator where it is, the generator will just learn to adversarial example the crap out of that discriminator. Yri i, i think that would go a bit wrong. Favour toos, the contrastive self. O, resolute lurning for again, but i so like what we've been talking about.
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