Foto del docente

Francesco Camilli

Fixed-term Researcher in Tenure Track L. 79/2022

Department of Mathematics

Academic discipline: MATH-04/A Mathematical Physics

News

How AI learns

Researchers at ICTP use theoretical physics to shed light on how deep neural networks learn

A research group led by ICTP researcher Jean Barbier has recently developed a sharp theoretical description of learning in a certain class of deep neural networks, shedding light on the fundamental processes underlying these tools. Their results were recently published in Physical Review X.

Visit ICTP's website to read the full article.

Published on: July 29 2026