Machine Learning Street Talk (MLST) cover image

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

Machine Learning Street Talk (MLST)

00:00

Exploring Ranking Functions in Recognition Models

This chapter explores the complexities involved in creating a ranking function for recognition models, emphasizing the challenges of evaluating different functions' utility. It introduces a simple approach that ranks functions by generation probability while recognizing the uncertainties in determining the optimal number of functions to include.

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