位置：成果数据库 > 期刊 > 期刊详情页
A Modified Gradient-Based Neuro-Fuzzy Learning Algorithm for Pi-Sigma Network Based on First-Order Takagi-Sugeno System
  • ISSN号：2095-2651
  • 期刊名称：《数学研究及应用：英文版》
  • 时间：0
  • 分类：TP273.4[自动化与计算机技术—控制科学与工程;自动化与计算机技术—检测技术与自动化装置] TP18[自动化与计算机技术—控制科学与工程;自动化与计算机技术—控制理论与控制工程]
  • 作者机构：[1]School of Mathematical Sciences, Dalian University of Technology, Liaoning 116024, P. R. China, [2]School of Information Science and Engineering, Dalian Polytechnic University, Liaoning 116034, P. R. China
  • 相关基金：Supported by the Fundamental Research Funds for the Central Universities;; the National Natural Science Foundation of China （Grant No.11171367）;; the Youth Foundation of Dalian Polytechnic University （Grant No.QNJJ201308）
作者： Yan LIU[1,2], Jie YANG[1], Dakun YANG[1], Wei WU[1]
关键词： 模糊推理系统, 学习算法, 神经模糊, 梯度, 一阶, 网络, 误差函数, 强收敛性, first-order Takagi-Sugeno inference system, Pi-Sigma network, convergence.
中文摘要：

This paper presents a Pi-Sigma network to identify first-order Tagaki-Sugeno(T-S)fuzzy inference system and proposes a simplified gradient-based neuro-fuzzy learning algorithm.A comprehensive study on the weak and strong convergence for the learning method is made,which indicates that the sequence of error function goes to a fixed value,and the gradient of the error function goes to zero,respectively.

英文摘要：

This paper presents a Pi-Sigma network to identify first-order Tagaki-Sugeno（T-S） fuzzy inference system and proposes a simplified gradient-based neuro-fuzzy learning algorithm.A comprehensive study on the weak and strong convergence for the learning method is made,which indicates that the sequence of error function goes to a fixed value,and the gradient of the error function goes to zero,respectively.

同期刊论文项目
前馈神经网络学习算法的设计与分析
期刊论文 39 会议论文 8
同项目期刊论文
Is bias dispensable for fuzzy neural networks?
Convergence of gradient method with momentum for back-propagation neural networks
L-p approximation capability of RBF neural networks
Convergence of gradient method for Elman networks
A remark on the error-backpropagation learning algorithm for spiking neural networks
SOMO-m Optimization Algorithm with Multiple Winners
Fuzzy similarity-based nearest-neighbour classification as alternatives to their fuzzy-rough paralle
Extreme learning machine for interval neural networks
A Smoothing Interval Neural Network
A Modified Learning Algorithm for Interval Perceptrons with Interval Weights
Convergence of batch gradient learning algorithm with smoothing L1/2 regularization for Sigma-Pi-Sig
A Modified Spiking Neuron that Involves Derivative of the State Function at Firing Time
Convergence of approximated gradient method for Elman network
Training pi-sigma network by online gradient algorithm with penalty for small weight update
A modified gradient learning algorithm with smoothing L1/2 regularization for Takagi-Sugeno fuzzy m
A pruning algorithm with L1/2 regularizer for extreme learning machine
An Iterative Algorithm for Motif Discovery
Negative effects of sufficiently small initialweights on back-propagation neural networks
Computational properties and convergence analysis of BPNN for cyclic and almost cyclic learning with
基于蚁群迭代算法的近似测地线计算
An algorithm for motif discovery with iteration on lengths of motifs
Convergence Analysis of a New Self Organizing Map Based Optimization (SOMO) Algorithm
Kernel-based Fuzzy-rough Nearest-neighbour Classification for Mammographic Risk Analysis
A parameter conjugate gradientmethod based on secant equation for unconstrained optimization
Convergence of online gradient method for feedforward neural networks with smoothing L 1/2 regulariz
Negative effects of sufficiently small initial weights on back-propagation neural networks
A pruning algorithm with L1/2 regularizer for extreme learning machine
期刊信息
  • 《数学研究及应用：英文版》
  • 中国科技核心期刊
  • 主管单位:国家教育部
  • 主办单位:大连理工大学
  • 主编：王仁宏
  • 地址：大连理工大学应用数学系
  • 邮编：116024
  • 邮箱：
  • 电话：0411-84707392
  • 国际标准刊号：ISSN：2095-2651
  • 国内统一刊号：ISSN：21-1579/O1
  • 邮发代号:8-92
  • 获奖情况:
  • 1998年大连市优秀期刊奖,2000年大连市优秀期刊奖
  • 国内外数据库收录:
  • 俄罗斯文摘杂志,美国数学评论（网络版）,德国数学文摘,日本日本科学技术振兴机构数据库,中国中国科技核心期刊
  • 被引量:36