文献类型：期刊文献

英文题名：Evolving Dual-Threshold Bienenstock-Cooper-Munro Learning Rules in Echo State Networks

作者：Wang, Xinjie[1];Jin, Yaochu[1,2];Du, Wenli[1];Wang, Jun[3,4]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Univ Surrey, Dept Comp Sci, Guildford GU2 7XH, Surrey, England;[3]City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China;[4]City Univ Hong Kong, Sch Data Sci, Hong Kong, Peoples R China

年份：2024

卷号：35

期号：2

起止页码：1572

外文期刊名：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录：;EI(收录号：20222812350210);WOS:【SCI-EXPANDED(收录号:WOS:000821550600001)】；

基金：This work was supported in part by the Key Project of Science and Technology Innovation 2030 through the Ministry of Science and Technology of China under Grant 2018AAA0101302, in part by the National Natural Science Foundation of China (Basic Science Center Program) under Grant 61988101, in part by the National Science Fund for Distinguished Young Scholars under Grant 61725301 and Grant 61925305, in part by the Shanghai Sailing Program under Grant 21YF1409900, and in part by the National Natural Science Foundation of China under Grant 62003140.

语种：英文

外文关键词：Reservoirs; Neurons; Depression; Biology; Topology; Synapses; Optimization; Bienenstock-Cooper-Munro (BCM) learning rule; covariance matrix adaptation evolution strategy; dual-threshold; echo state networks (ESNs); regression

摘要：The strengthening and the weakening of synaptic strength in existing Bienenstock-Cooper-Munro (BCM) learning rule are determined by a long-term potentiation (LTP) sliding modification threshold and the afferent synaptic activities. However, synaptic long-term depression (LTD) even affects low-active synapses during the induction of synaptic plasticity, which may lead to information loss. Biological experiments have found another LTD threshold that can induce either potentiation or depression or no change, even at the activated synapses. In addition, existing BCM learning rules can only select a set of fixed rule parameters, which is biologically implausible and practically inflexible to learn the structural information of input signals. In this article, an evolved dual-threshold BCM learning rule is proposed to regulate the reservoir internal connection weights of the echo-state-network (ESN), which can contribute to alleviating information loss and enhancing learning performance by introducing different optimal LTD thresholds for different postsynaptic neurons. Our experimental results show that the evolved dual-threshold BCM learning rule can result in the synergistic learning of different plasticity rules, effectively improving the learning performance of an ESN in comparison with existing neural plasticity learning rules and some state-of-the-art ESN variants on three widely used benchmark tasks and the prediction of an esterification process.