2min snip

Machine Learning Street Talk (MLST) cover image

Dr. Thomas Parr - Active Inference Book

Machine Learning Street Talk (MLST)

NOTE

Understanding Active Inference

Active inference is described in the book as a concept used by biological organisms to resist entropic forces by minimizing their free energy. The approach is detailed from both a high-level, helicopter view perspective and a more mechanistic, mathematical viewpoint. The high road discusses the why and how of active inference, while the low road delves into Bayesian mechanics, probability theory, variational inference, and framing active inference as a process theory. Professor Karl Fristen highlights that active inference is a way to comprehend sentient behavior by engaging in actively sampling the world, perceiving as hypothesis testing, and planning as inference to resolve uncertainty about the lived world.

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