人工神经网络
计算机科学
培训(气象学)
物理系统
人工智能
物理
量子力学
气象学
作者
James C. Spall,Xianxin Guo,Alexander I. Lvovsky
出处
期刊:Frontiers in Optics
[Optica Publishing Group]
日期:2022-01-01
卷期号:: FTu6D.2-FTu6D.2
被引量:5
标识
DOI:10.1364/fio.2022.ftu6d.2
摘要
Optical neural networks are often trained “in-silico” on digital simulators, but physical imperfections that cannot be modelled may lead to a “reality gap” between the simulator and the physical system. In this work we present hybrid training, where the weight matrix is trained by computing neuron values optically using the actual physical network.
科研通智能强力驱动
Strongly Powered by AbleSci AI