Physical neural networks with self-learning capabilities

作     者：Weichao Yu Hangwen Guo Jiang Xiao Jian Shen 

作者机构：State Key Laboratory of Surface Physics and Institute for Nanoelectronic Devices and Quantum ComputingFudan UniversityShanghai 200433China Zhangjiang Fudan International Innovation CenterFudan UniversityShanghai 201210China Department of PhysicsFudan UniversityShanghai 200433China Shanghai Research Center for Quantum SciencesShanghai 201315China Collaborative Innovation Center of Advanced MicrostructuresNanjing 210093China 

出 版 物：《Science China(Physics,Mechanics & Astronomy)》 (中国科学：物理学、力学、天文学（英文版）)

年 卷 期：2024年第67卷第8期

页      面：23-42页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key Research and Development Program of China(Grant Nos.2022YFA1403300,and 2020YFA0309100) the National Natural Science Foundation of China(Grant Nos.12204107,and 12074073) Shanghai Municipal Science and Technology Major Project(Grant No.2019SHZDZX01) Shanghai Pujiang Program(Grant No.21PJ1401500) Shanghai Science and Technology Committee(Grant Nos.21JC1406200,and 20JC1415900) 

主　　题：self-learning physical neural networks neuromorphic computing physical learning 

摘      要：Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or *** networks harness the distinctive characteristics of physical systems to carry out computations effectively,potentially surpassing the constraints of conventional digital neural networks.A recent advancement known as“physical self-learningaims to achieve learning through intrinsic physical processes rather than relying on external *** article offers a comprehensive review of the progress made in implementing physical self-learning across various physical *** learning strategies that contribute to the realization of physical self-learning are *** challenges in understanding the fundamental mechanism of learning,this work highlights the progress towards constructing intelligent hardware from the ground up,incorporating embedded self-organizing and self-adaptive dynamics in physical systems.