3min chapter

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis cover image

E39: Seeing is Believing with MIT’s Ziming Liu

"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

CHAPTER

The Unreasonably Effectiveness of Smooth Activation Functions

In this particular case of x2 squared plus sign of pi x4, it is really just a couple of neurons that are doing the job. And I'm I'm left feeling like this is a Eureka breakthrough in the sense that, oh my God, you know, look how simple the structure is. So essentially, there's only five total active neurons that are needed to translate these two inputs to that functional form output. That seems like Eureka, but then, if I could be vulnerable with you for a second, I still don't really get how it's doing it.

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