Skip to main content
Springer Nature Link
Log in

A New Training Algorithm for a Fuzzy Perceptron and Its Convergence

  • Conference paper
Advances in Neural Networks – ISNN 2005 (ISNN 2005)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3496))

Included in the following conference series:

Abstract

In this paper, we present a new training algorithm for a fuzzy perceptron. In the case where the dimension of the input vectors is two and the training examples are separable, we can prove a finite convergence, i.e., the training procedure for the network weights will stop after finite steps. When the dimension is greater than two, stronger conditions are needed to guarantee the finite convergence.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Nikov, A., Stoeva, S.: Quick Fuzzy Backpropagation Algorithm. Neural Networks 14, 231–244 (2001)

    Article  Google Scholar 

  2. Castro, J.L., Delgado, M., Mantas, C.J.: A Fuzzy Rule-based Algorithm to Train Perceptrons. Fuzzy Sets and Systems 118, 359–367 (2001)

    Article  MATH  MathSciNet  Google Scholar 

  3. Pandit, M., Srivastava, L., Sharma, J.: Voltage Contingency Ranking Using Fuzzified Multilayer Perceptron. Electric Power Systems Research 59, 65–73 (2001)

    Article  Google Scholar 

  4. Chowdhury, P., Shukla, K.K.: Incorporating Fuzzy Concepts along with Dynamic Tunneling for Fast and Robust Training ofMultilayer Perceptrons. Neurocomputing 50, 319–340 (2003)

    Article  Google Scholar 

  5. Stoeva, S., Nikov, A.: A Fuzzy Backpropagation Algorithm. Fuzzy Sets and Systems 112, 27–39 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  6. Liang, Y.C., Feng, D.P., Lee, H.P., Lim, S.P., Lee, K.H.: Successive Approximation Training Algorithm for Feedforward Neural Networks. Neurocomputing 42, 311–322 (2002)

    Article  MATH  Google Scholar 

  7. Wu, W., Shao, Z.: Convergence of Online Gradient Methods for Continuous perceptrons with Linearly Separable Training Patterns. Applied Mathematics Letters 16, 999–1002 (2003)

    Article  MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dept. Appl. Math., Dalian University of Technology, Dalian, 116023, China

    Jie Yang, Wei Wu & Zhiqiong Shao

  2. Math. Dept., Dalian Maritime University, Dalian, 116000, China

    Wei Wu

Authors
  1. Jie Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Wei Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhiqiong Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong, China

    Jun Wang

  2. The Key Laboratory of Optoelectric Technology & Systems, Ministry of Education, China

    Xiaofeng Liao

  3. Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, 610054, Chengdu, P.R. China

    Zhang Yi

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yang, J., Wu, W., Shao, Z. (2005). A New Training Algorithm for a Fuzzy Perceptron and Its Convergence. In: Wang, J., Liao, X., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427391_97

Download citation

  • DOI: https://doi.org/10.1007/11427391_97

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-25912-1

  • Online ISBN: 978-3-540-32065-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation