To the role of the choice of the neuron model in spiking network learning on base of Spike-Timing-Dependent Plasticity

被引：5

作者：

Sboev, Alexander ^{[1
,2
]}

Rybka, Roman ^{[1
]}

Serenko, Alexey ^{[1
]}

Vlasov, Danila ^{[1
,2
]}

Kudryashov, Nikolay ^{[1
,2
]}

Demin, Vyacheslav ^{[1
]}

机构：

[1] Natl Res Ctr, Kurchatov Inst, Moscow, Russia

[2] MEPhI Natl Res Nucl Univ, Moscow, Russia

来源：

8TH ANNUAL INTERNATIONAL CONFERENCE ON BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES, BICA 2017 (EIGHTH ANNUAL MEETING OF THE BICA SOCIETY) | 2018年 / 123卷

基金：

俄罗斯科学基金会;

关键词：

spike-timing-dependent plasticity; long-term synaptic plasticity; spiking neural networks; computational neuroscience;

D O I：

10.1016/j.procs.2018.01.066

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The goal of this work is to study the influence of the neuron model choice on the results of STDP learning on base of simple toy tasks. As shown, the resulting mean output firing rate after STDP learning with restricted symmetric spike pairing scheme does not depend on the mean input rates for such neuron models as Leaky Integrate-and-Fire, Traub, and static neuron. Then this effect, being used to solve a typical classification task of Fishers Iris, demonstrates that the classification accuracy does not depend significantly on the choice of the neuron model. Thus, the independence of learning results on the neuron model gives the possibility to use simpler neuron models in further investigations. (C) 2018 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/3.0/) Peer-review under responsibility of the scientific committee of the 8th Annual International Conference on Biologically Inspired Cognitive Architectures

引用

页码：432 / 439

页数：8

共 20 条

[1] Synaptic plasticity: taming the beast [J].