树突神经元模型及其逼近能力

2019 6th International Conference on Systems and Informatics (ICSAI) Pub Date : 2019-11-01 DOI:10.1109/ICSAI48974.2019.9010147

Fei Teng, Yuki Todo

{"title":"树突神经元模型及其逼近能力","authors":"Fei Teng, Yuki Todo","doi":"10.1109/ICSAI48974.2019.9010147","DOIUrl":null,"url":null,"abstract":"Recently, an artificial neural network (ANN) named dendritic neuron model has been proposed which mimics the nonlinear interaction in the signal processing in a neuron. in order to research the approximation performance of this model, this paper use the mathematical theory to prove that single dendritic neuron model neuron is able to approximate any Borel measurable function to any desired degree of accuracy.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"04 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Dendritic Neuron Model and Its Capability of Approximation\",\"authors\":\"Fei Teng, Yuki Todo\",\"doi\":\"10.1109/ICSAI48974.2019.9010147\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, an artificial neural network (ANN) named dendritic neuron model has been proposed which mimics the nonlinear interaction in the signal processing in a neuron. in order to research the approximation performance of this model, this paper use the mathematical theory to prove that single dendritic neuron model neuron is able to approximate any Borel measurable function to any desired degree of accuracy.\",\"PeriodicalId\":270809,\"journal\":{\"name\":\"2019 6th International Conference on Systems and Informatics (ICSAI)\",\"volume\":\"04 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 6th International Conference on Systems and Informatics (ICSAI)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICSAI48974.2019.9010147\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 6th International Conference on Systems and Informatics (ICSAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSAI48974.2019.9010147","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

近年来，人们提出了一种模拟神经元信号处理过程中非线性相互作用的人工神经网络——树突神经元模型。为了研究该模型的逼近性能，本文利用数学理论证明了单个树突神经元模型神经元能够逼近任意Borel可测函数达到任意精度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Dendritic Neuron Model and Its Capability of Approximation

Recently, an artificial neural network (ANN) named dendritic neuron model has been proposed which mimics the nonlinear interaction in the signal processing in a neuron. in order to research the approximation performance of this model, this paper use the mathematical theory to prove that single dendritic neuron model neuron is able to approximate any Borel measurable function to any desired degree of accuracy.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2019 6th International Conference on Systems and Informatics (ICSAI)

自引率

0.00%

发文量