Home>Results

  • Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

[会议论文]

A Spiking-based mechanism for self-organizing RBF neural networks

Share
Edit Delete 报错

Author:

Han, Honggui (Han, Honggui.) (Scholars:韩红桂) | Wang, Lidan (Wang, Lidan.) | Qiao, Junfei (Qiao, Junfei.) (Scholars:乔俊飞) | Unfold

Indexed by:

EI Scopus

Abstract:

In this paper, a spiking growing algorithm (SGA) is proposed for optimizing the structure of radial basis function (RBF) neural network. Inspired by the synchronous behavior of spiking neurons, the spiking strength (ss) of the hidden neurons is defined as the criteria of SGA, which investigates a new way to simulate the connections between hidden and output neurons of RBF neural network. This SGA-based RBF (SGA-RBF) neural network can self-organize the hidden neurons online, to achieve the appropriate network efficiency. Meanwhile, to ensure the accuracy of SGA-RBF neural network, the structure-adjusting and parameters-training phases are performed simultaneously. Simulation results demonstrate that the proposed method can obtain a higher precision in comparison with some other existing methods. © 2014 IEEE.

Keyword:

Functions Radial basis function networks Nonlinear systems Neurons

Author Community:

  • [ 1 ] [Han, Honggui]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, China
  • [ 2 ] [Han, Honggui]Department of Mechanical and Biomedical Engineering, City University of Hong Kong, Kowloon, Hong Kong
  • [ 3 ] [Wang, Lidan]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, China
  • [ 4 ] [Qiao, Junfei]College of Electronic and Control Engineering, Beijing University of Technology, Beijing, China
  • [ 5 ] [Feng, Gang]Department of Mechanical and Biomedical Engineering, City University of Hong Kong, Kowloon, Hong Kong
  • [ 6 ] [Feng, Gang]Nanjing University of Science and Technology, Nanjing; 210094, China

Reprint Author's Address:

  • 韩红桂

    [han, honggui]department of mechanical and biomedical engineering, city university of hong kong, kowloon, hong kong;;[han, honggui]college of electronic and control engineering, beijing university of technology, beijing, china

Show more details

Related Article:

Source :

Year: 2014

Page: 3775-3782

Language: English

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count: 5

30 Days PV: 4

Online/Total:450/6058548
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.