Streamlined photonic reservoir computer with augmented memory capabilities  

作　　者：Changdi Zhou Yu Huang Yigong Yang Deyu Cai Pei Zhou Kuenyao Lau Nianqiang Li Xiaofeng Li 

机构地区：[1]School of Optoelectronic Science and Engineering&Collaborative Innovation Center of Suzhou Nano Science and Technology,Soochow University,Suzhou 215006,China [2]Key Lab of Advanced Optical Manufacturing Technologies of Jiangsu Province&Key Lab of Modern Optical Technologies of Education Ministry of China,Soochow University,Suzhou 215006,China

出　　处：《Opto-Electronic Advances》2025年第1期45-57,共13页光电进展(英文)

基　　金：National Natural Science Foundation of China(62171305,62405206,62004135,62001317,62111530301);Natural Science Foundation of Jiangsu Province(BK20240778,BK20241917);State Key Laboratory of Advanced Optical Communication Systems and Networks,China(2023GZKF08);China Postdoctoral Science Foundation(2024M752314);Postdoctoral Fellowship Program of CPSF(GZC20231883);Innovative and Entrepreneurial Talent Program of Jiangsu Province(JSSCRC2021527).

摘　　要：Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While such a computing paradigm can only employ a single photonic device as the nonlinear node for data processing,the performance highly relies on the fading memory provided by the delay feedback loop(FL),which sets a restriction on the extensibility of physical implementation,especially for highly integrated chips.Here,we present a simplified photonic scheme for more flexible parameter configurations leveraging the designed quasi-convolution coding(QC),which completely gets rid of the dependence on FL.Unlike delay-based TDRC,encoded data in QC-based RC(QRC)enables temporal feature extraction,facilitating augmented memory capabilities.Thus,our proposed QRC is enabled to deal with time-related tasks or sequential data without the implementation of FL.Furthermore,we can implement this hardware with a low-power,easily integrable vertical-cavity surface-emitting laser for high-performance parallel processing.We illustrate the concept validation through simulation and experimental comparison of QRC and TDRC,wherein the simpler-structured QRC outperforms across various benchmark tasks.Our results may underscore an auspicious solution for the hardware implementation of deep neural networks.

关 键 词：photonic reservoir computing machine learning vertical-cavity surface-emitting laser quasi-convolution coding augmented memory capabilities 

分 类 号：TP333[自动化与计算机技术—计算机系统结构] TN248[自动化与计算机技术—计算机科学与技术] TP181[电子电信—物理电子学]