✳flâneur — a map of the web's best reading

Distilling Singular Learning Theory - LessWrong

lesswrong.com · 147 words · saved by 1 readers

This sequence distills Sumio Watanabe's Singular Learning Theory (SLT) by explaining the essence of its main theorem - Watanabe's Free Energy Formula for Singular Models - and illustrating its implications with intuition-building examples. I show why neural networks are singular models, and demonstrate how SLT provides a framework for understanding phases and phase transitions in neural networks.

x Distilling Singular Learning Theory — LessWrong Distilling Singular Learning Theory Jun 16, 2023 by Liam Carroll This sequence distills Sumio Watanabe's Singular Learning Theory (SLT) by explaining the essence of its main theorem - Watanabe's Free Energy Formula for Singular Models - and illustrating its implications with intuition-building examples. I show why neural networks are singular models, and demonstrate how SLT provides a framework for understanding phases and phase transitions in neural networks. 97 DSLT 0. Distilling Singular Learning Theory Ω Liam Carroll 3y Ω 8 62 DSLT 1. The R

Explore this link on the map →

related reading