Physical neural networks with self-learning capabilities  

作　　者：Weichao Yu Hangwen Guo Jiang Xiao Jian Shen 

机构地区：[1]State Key Laboratory of Surface Physics and Institute for Nanoelectronic Devices and Quantum Computing,Fudan University,Shanghai 200433,China [2]Zhangjiang Fudan International Innovation Center,Fudan University,Shanghai 201210,China [3]Department of Physics,Fudan University,Shanghai 200433,China [4]Shanghai Research Center for Quantum Sciences,Shanghai 201315,China [5]Collaborative Innovation Center of Advanced Microstructures,Nanjing 210093,China

出　　处：《Science China(Physics,Mechanics & Astronomy)》2024年第8期23-42,共20页中国科学：物理学、力学、天文学（英文版）

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)。

摘　　要：Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials.These 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-learning”aims to achieve learning through intrinsic physical processes rather than relying on external computations.This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems.Prevailing learning strategies that contribute to the realization of physical self-learning are discussed.Despite 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.

关 键 词：SELF-LEARNING physical neural networks neuromorphic computing physical learning 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]