文献类型：期刊文献

英文题名：Synergies between synaptic and intrinsic plasticity in echo state networks

作者：Wang, Xinjie[1,2];Jin, Yaochu[1,2,3];Hao, Kuangrong[2]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Donghua Univ, Coll Informat Sci & Technol, Engn Res Ctr Digitized Text & Apparel Technol, Minist Educ, Shanghai 201620, Peoples R China;[3]Univ Surrey, Dept Comp Sci, Nat Inspired Comp & Engn, Guildford, Surrey, England

年份：2021

卷号：432

起止页码：32

外文期刊名：NEUROCOMPUTING

收录：;EI(收录号：20210209752552);WOS:【SCI-EXPANDED(收录号:WOS:000620905000004)】；

基金：This work was supported in part by the Fundamental Research Funds for the Central Universities under Grant CUSF-DH-D2018101 and Grant 2232016D-32, in part by the National Nature Science Foundation of China under Grant 61473078, Grant 61503075, and Grant 61603090, in part by the International Collaborative Project of the Shanghai Committee of Science and Technology under Grant 16510711100, in part by the Agricultural Project of the Shanghai Committee of Science and Technology under Grant 16391902800, in part by the Shanghai Science and Technology Promotion Project from Shanghai Municipal Agriculture Commission under Grant 2016-1-5-12.

语种：英文

外文关键词：Echo state networks; Synaptic plasticity; Intrinsic plasticity; Synergistic learning; Regression; Classification

摘要：Synaptic plasticity and intrinsic plasticity, as two of the most common neural plasticity mechanisms, occur in all neural circuits throughout life. Neurobiological studies indicated that the interplay between synaptic and intrinsic plasticity contributes to the adaptation of the nervous system to different synaptic input signals. However, most existing computational models of neural plasticity consider these two plasticity mechanisms separately, which is biologically implausible. In this paper, a synergistic plasticity learning rule is proposed to adapt the reservoir connections in echo state networks (ESNs), which not only takes into account the regulation of synaptic weights, but also considers the adjustment of neuronal intrinsic excitability. The proposed synergetic plasticity rule is verified on a number of prediction and classification benchmark problems and our empirical results demonstrate that the ESN with synergistic plasticity learning rule performs much better than the state-of-the-art ESN models, and an ESN with a single neural plasticity rule. (c) 2020 Elsevier B.V. All rights reserved.