3min chapter

Machine Learning Street Talk (MLST) cover image

#033 Prof. Karl Friston - The Free Energy Principle

Machine Learning Street Talk (MLST)

CHAPTER

The Free Energy Principle Equally Weights Accuracy and Complexity

The free energy principle equally weights accuracy and complexity. Might it be the case that we need to have a temperature parameter, like a kind of nod to tweak the relative contribution between accuracy and complexity? Would such aparameter be useful? I'm wondering is in the free energy principle term with the complexity. There are ongoing debates amongst the younger people who love the maths of this about whether we're just in a generic K-L divergence or whether we need to exclude it to get to expected free energy. So that's again an open question, which I'm hoping will be resolved in about a year's time, at which point your alpha will occur and I'll try to call it alpha in

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