Machine Learning Street Talk (MLST) cover image

THE HARD PROBLEM OF OBSERVERS - WOLFRAM & FRISTON [SPECIAL EDITION]

Machine Learning Street Talk (MLST)

00:00

The Role of Maximizing Marginal Likelihood applied through the Markov blanket

Measuring devices or our senses combine different states of the world to create a simple summary/nInner processes are hidden behind the Markov blanket and only the behavior and sensory impressions are observable/nThe goal is to find the most accurate and simple explanation for sensory impressions/nCompression and course-graining emerge from maximizing the marginal likelihood of sensory exchanges

Transcript
Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
App store bannerPlay store banner
Get the app