Towards mixed physical node reservoir computing:light-emitting synaptic reservoir system with dual photoelectric output  

作　　者：Minrui Lian Changsong Gao Zhenyuan Lin Liuting Shan Cong Chen Yi Zou Enping Cheng Changfei Liu Tailiang Guo Wei Chen Huipeng Chen 

机构地区：[1]Institute of Optoelectronic Display,National&Local United Engineering Lab of Flat Panel Display Technology,Fuzhou University,Fuzhou 350002,China [2]Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China,Fuzhou 350100,China [3]Joint School of National University of Singapore and Tianjin University,International Campus of Tianjin University,Fuzhou 350207,China [4]Department of Chemistry,National University of Singapore,3 Science Drive 3,Singapore 117543,Singapore [5]Department of Physics,National University of Singapore,3 Science Drive 3,Singapore 117543,Singapore

出　　处：《Light(Science & Applications)》2024年第9期1865-1877,共13页光（科学与应用)（英文版）

基　　金：financial support from the National Natural Science Foundation of China(62374033,62274118);Singapore National Research Foundation Investigator ship under Grant No NRF-NRFI08-2022-0009;Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China(2021ZZ129).

摘　　要：Memristor-based physical reservoir computing holds significant potential for efficiently processing complex spatiotemporal data,which is crucial for advancing artificial intelligence.However,owing to the single physical node mapping characteristic of traditional memristor reservoir computing,it inevitably induces high repeatability of eigenvalues to a certain extent and significantly limits the efficiency and performance of memristor-based reservoir computing for complex tasks.Hence,this work firstly reports an artificial light-emitting synaptic(LES)device with dual photoelectric output for reservoir computing,and a reservoir system with mixed physical nodes is proposed.The system effectively transforms the input signal into two eigenvalue outputs using a mixed physical node reservoir comprising distinct physical quantities,namely optical output with nonlinear optical effects and electrical output with memory characteristics.Unlike previously reported memristor-based reservoir systems,which pursue rich reservoir states in one physical dimension,our mixed physical node reservoir system can obtain reservoir states in two physical dimensions with one input without increasing the number and types of devices.The recognition rate of the artificial light-emitting synaptic reservoir system can achieve 97.22%in MNIST recognition.Furthermore,the recognition task of multichannel images can be realized through the nonlinear mapping of the photoelectric dual reservoir,resulting in a recognition accuracy of 99.25%.The mixed physical node reservoir computing proposed in this work is promising for implementing the development of photoelectric mixed neural networks and material-algorithm collaborative design.

关 键 词：RESERVOIR MIXED system 

分 类 号：TP333[自动化与计算机技术—计算机系统结构]