多路复用
计算机科学
油藏计算
光子学
水准点(测量)
实施
频域
编码
级联
电子工程
足迹
利用
光学
计算机硬件
电信
物理
人工智能
工程类
人工神经网络
大地测量学
基因
循环神经网络
古生物学
生物
化学
生物化学
程序设计语言
地理
计算机视觉
计算机安全
化学工程
作者
Lorenz Butschek,Akram Akrout,Evangelia Dimitriadou,Alessandro Lupo,Marc Haelterman,Serge Massar
出处
期刊:Optics Letters
[Optica Publishing Group]
日期:2022-02-03
卷期号:47 (4): 782-782
被引量:12
摘要
Reservoir computing is a brain-inspired approach for information processing, well suited to analog implementations. We report a photonic implementation of a reservoir computer that exploits frequency domain multiplexing to encode neuron states. The system processes 25 comb lines simultaneously (i.e., 25 neurons), at a rate of 20 MHz. We illustrate performances on two standard benchmark tasks: channel equalization and time series forecasting. We also demonstrate that frequency multiplexing allows output weights to be implemented in the optical domain, through optical attenuation. We discuss the perspectives for high-speed, high-performance, low-footprint implementations.
科研通智能强力驱动
Strongly Powered by AbleSci AI