ELSC News

New Theory Cracks Open the Black Box of Deep Learning

September 24, 2017

New Theory Cracks Open the Black Box of Deep Learning

A scientific breakthrough done by ELSC researcher, Prof. Naftali Tishby and his students, Noga Zaslavsky and Ravid Ziv.

A new idea called the “information bottleneck” is helping to explain the puzzling success of today’s artificial-intelligence algorithms — and might also explain how human brains learn.

 

Naftali Tishby, a computer scientist and neuroscientist from the Hebrew University of Jerusalem, presented evidence in support of a new theory explaining how deep learning works. Tishby argues that deep neural networks learn according to a procedure called the “information bottleneck,” 

 

Read more.

Tags: