2min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yann LeCun and Energy-Based Models

Machine Learning Street Talk (MLST)

CHAPTER

Is the Energy Function Differential?

The energy function is not used as part of the training process, because it is. What is always comes by what you put into the energy function. It's like if i was taking my gene or and then i'm trying to, like, now search along those z imputs to get the most realistic output. You can essentially find the z that will most accurately reconstruct that particular data point. Butit is not the meaning of a gan rit r looking for something whereyou actively do what he said at the beginning, you should set out to do.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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