4min chapter

Machine Learning Street Talk (MLST) cover image

#033 Prof. Karl Friston - The Free Energy Principle

Machine Learning Street Talk (MLST)

CHAPTER

The Benefits of Removing the Alpha or Beta Coefficient on the Complexity Versus the Accuracy Dilemma

If you're just trying to explain the necessary properties dynamics of systems that self-organised, you are saying nothing about the nature of that steady state other than it is at steady state. It could be very high entropy steady state, it could be very low entropy steady state,. You haven't really committed to any kind of steady state which means that it's slightly disingenuous to say that the imperative for everything is to minimise say a free energy function. In bi-acknowaging, there are different kinds of non-equilibrium steady states and that in so doing, you have to really think about the relative importance for this steady state of technically the risk and the ambiguity and the sensory

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