AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
#67 Prof. KARL FRISTON 2.0
Machine Learning Street Talk (MLST)
The Separation of Temple Scales
Inference and learning can contextulize each other. To optimise the weights of deep nor network, or the prameters of variation altri coda or gemitanbecenial network, you have to do it after you've done some inference. The way in which you optimize the fast of the slow stuff depends very much on having an optimal inference scheme at the fast level. And this would prick us back to this mo, evolution and modern selection and structure learning. It also tells you, well, the stuff all the way up in ter f the separation table scale is quite a fundamental difference between infering and learning.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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