Machine Learning Street Talk (MLST) cover image

Decompiling Dreams: A New Approach to ARC? - Alessandro Palmarini

Machine Learning Street Talk (MLST)

00:00

Exploring Conditional Probabilities and Function Chunking

This chapter explores the Bernoulli distribution and its role in evaluating function chunking for recognition models. It highlights the effectiveness of a caching scheme that measures the utility of chunking functions compared to generating full programs within neural search policies.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app