3min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Machine Learning Street Talk (MLST)

CHAPTER

Is This a Supervised Learning Way of Disentangling the Representations?

So it's like a supervised learning way of disentangling the representations from the z space. We don't know if our processing comes from generative modelling the data or purely discriminative modelling. But thegenerative hypothesis would explain, for example, why you're so good at recognizing out of distribution samples? Because with a generative model, you get that for free. You can simply say, this data point, it doesn't fit into any of my classes, right into any ofMyData. If you were just a discriminate ive machine, you would not do that. Is very interesting.

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