Computer Scientists Prove Why Bigger Neural Networks Do Better

Share this content

Published:
February 15, 2022

A recent article in Quanta Magazine explored why neural networks must be much larger than conventionally expected. The findings, which come from a paper by Sébastien Bubeck of Microsoft Research and Mark Sellke of Stanford University, give some insight into a question that has come up repeatedly over several decades.

WNCG professor Alex Dimakis was quoted in the article, providing background on overparameterization in neural networks.

Read the article via quantamagazine.org.

More information

https://www.quantamagazine.org/computer-scientists-prove-why-bigger-neural-networks-do-better-20220210/

News category:
General
News tags:
WNCG in the media