文章基本信息

标题：Boolean learning under noise-perturbations in hardware neural networks
本地全文：下载
作者：Louis Andreoli ; Xavier Porte ; Stéphane Chrétien 等
期刊名称：Nanophotonics
印刷版ISSN：2192-8606
电子版ISSN：2192-8614
出版年度：2020
卷号：-1
期号：ahead-of-print
页码：4139-4147
DOI：10.1515/nanoph-2020-0171
出版社：Walter de Gruyter GmbH
摘要：A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems have recently implemented some or all of these operations, yet the focus was placed on addressing technological challenges. Fundamental questions regarding learning in hardware neural networks remain largely unexplored. Noise in particular is unavoidable in such architectures, and here we experimentally and theoretically investigate its interaction with a learning algorithm using an opto-electronic recurrent neural network. We find that noise strongly modifies the system’s path during convergence, and surprisingly fully decorrelates the final readout weight matrices. This highlights the importance of understanding architecture, noise and learning algorithm as interacting players, and therefore identifies the need for mathematical tools for noisy, analogue system optimization.
关键词：Boolean learning ; neural networks ; noise