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)
How to Train a Discriminator in a Different Landscape?
Gans are notoriously difficult to train and to train stably, exactly because of that. So what you need to do is to train them jointly so that you always keep it flat enough for the generator to come closer. And then the discriminator can well make it steeper, and then you get gradient. Ye, it does rit you back prop through the discriminator to the generator. The generator always knows in which way it needs to change too in order to fool the discriminator.
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