5min chapter

Machine Learning Street Talk (MLST) cover image

ICLR 2020: Yoshua Bengio and the Nature of Consciousness

Machine Learning Street Talk (MLST)

CHAPTER

Deep Learning Is Not Efficient

E bescre: We need a way to efficiently learn from large data, like abit lik yonder car sosithing. He also says that we need disti representations for generalization. But deep learning is not efficient even with the self supervised stuff it doesn't do anything to address the sample efficiency of deep learning. And i would say you probably have no better chance, that your model can be there in the real world than with the deep learning model.

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