학술논문
Physical deep learning with biologically inspired training method: gradient-free approach for physical hardware
Document Type
article
Author
Source
Nature Communications, Vol 13, Iss 1, Pp 1-12 (2022)
Subject
Language
English
ISSN
2041-1723
Abstract
Traditional learning procedures for artificial intelligence rely on digital methods not suitable for physical hardware. Here, Nakajima et al. demonstrate gradient-free physical deep learning by augmenting a biologically inspired algorithm, accelerating the computation speed on optoelectronic hardware.