5min chapter

Machine Learning Street Talk (MLST) cover image

#67 Prof. KARL FRISTON 2.0

Machine Learning Street Talk (MLST)

CHAPTER

Do the Markov Blankets Have to Be Zero?

In the paper you define ways in which, let's say, you can set various terms to zero. What i'm kind of wondering is, do they have to be zero? Like, what if this is generalized a bit to have like, a degree of active stateness and a degree of sensory stateness,. And would that give us any useful, useful outcomes mathematically? Or would it just get in the way, and it's just more convenient to continuezeroing out certain elements of the matrix?, he asks.

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