Physics solves a training problem for artificial neural networks
成果类型：
Editorial Material
署名作者：
Querlioz, Damien
署名单位：
Institut Polytechnique de Paris; Ecole Polytechnique; Centre National de la Recherche Scientifique (CNRS); Universite Paris Saclay; Universite Paris Cite
刊物名称：
Nature
ISSN/ISSBN：
0028-5033
DOI：
10.1038/d41586-024-02392-8
发表日期：
2024-08-08
页码：
264-265
关键词：
摘要：
Systems that emulate biological neural networks offer an efficient way of running AI algorithms, but they can't be trained using the conventional approach. The symmetry of these 'physical' networks provides a neat solution.