#033 Prof. Karl Friston - The Free Energy Principle

This week Dr. Tim Scarfe, Dr. Keith Duggar and Connor Leahy chat with Prof. Karl Friston. Professor Friston is a British neuroscientist at University College London and an authority on brain imaging. In 2016 he was ranked the most influential neuroscientist on Semantic Scholar.  His main contribution to theoretical neurobiology is the variational Free energy principle, also known as active inference in the Bayesian brain. The FEP is a formal statement that the existential imperative for any system which survives in the changing world can be cast as an inference problem. Bayesian Brain Hypothesis states that the brain is confronted with ambiguous sensory evidence, which it interprets by making inferences about the hidden states which caused the sensory data. So is the brain an inference engine? The key concept separating Friston's idea from traditional stochastic reinforcement learning methods and even Bayesian reinforcement learning is moving away from goal-directed optimisation.

Remember to subscribe! Enjoy the show!

00:00:00 Show teaser intro 

00:16:24 Main formalism for FEP 

00:28:29 Path Integral 

00:30:52 How did we feel talking to friston? 

00:34:06 Skit - on cultures (checked, but maybe make shorter) 

00:36:02 Friston joins 

00:36:33 Main show introduction 

00:40:51 Is prediction all it takes for intelligence? 

00:48:21 balancing accuracy with flexibility 

00:57:36 belief-free vs belief-based; beliefs are crucial  

01:04:53 Fuzzy Markov Blankets and Wandering Sets  

01:12:37 The Free Energy Principle conforms to itself  

01:14:50 useful false beliefs 

01:19:14 complexity minimization is the heart of free energy [01:19:14 ]Keith:  

01:23:25 An Alpha to tip the scales? Absoute not! Absolutely yes!  

01:28:47 FEP applied to brain anatomy  

01:36:28 Are there multiple non-FEP forms in the brain? 

01:43:11 a positive conneciton to backpropagation  

01:47:12 The FEP does not explain the origin of FEP systems  

01:49:32 Post-show banter 

https://www.fil.ion.ucl.ac.uk/~karl/

#machinelearning