Skip to main content
SpringerLink
Log in

BP Learning and Numerical Algorithm of Dynamic Systems

  • Conference paper
AI 2005: Advances in Artificial Intelligence (AI 2005)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3809))

Included in the following conference series:

  • 2396 Accesses

Abstract

This paper deals with relationship between BP learning for neural networks and numerical algorithm of differential equations. It is proposed that the iteration formula of BP algorithm is equivalent to Euler method of differential dynamic system under certain conditions, and the asymptotic solutions of the two formulas are consistent. It is also proved in theoretic that asymptotic solutions given by BP algorithm are equivalent to that computed by any numerical method for differential dynamic systems under certain conditions. Also, an example to train the BP network by modified numerical method is presented.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel Distributed Proceeding, pp. 318–362. MIT Press, Cambridge (1986)

    Google Scholar 

  2. Reyneri, L.M., Filippi, E.: Modified backpropagation algorithm for fast learning in neural networks. Electronics letters 26(19), 1564–1566 (1990)

    Article  Google Scholar 

  3. Qiu, G., Varley, M.R., Terrell, T.J.: Accelerated training of backpropagation neural networks by using adaptive momentum step. Electronics letters 28(4), 377–379 (1992)

    Article  Google Scholar 

  4. Roychowdhury, P., Singh, Y.P., Chansarkar, R.A.: Dynamic Tunneling Technique for Efficient Training of Multilayer pecoptron. IEEE transactions on neural networks 10(1), 48–55 (1999)

    Article  Google Scholar 

  5. Liang, J.Z., He, X.G., Zhou, J.Q.: Dynamic analysis of BP algorithm for neural networks. Acta Automatica Sinica 28(5), 729–735 (2002)

    MathSciNet  Google Scholar 

  6. Huang, L.: Stability Theory. Beijing University Press, Beijing (1992)

    Google Scholar 

  7. Liang, J.Z., He, X.G.: Research on approximation theory of fuzzy neural networks and learning algorithm, Beijing University of Aeronautics and Astronautics, Beijing, PhD dissertation (June 2001)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. College of Information Science and Engineering, Zhejiang Normal University, Jinhua, 321004, China

    Jiuzhen Liang & Hong Jiang

Authors
  1. Jiuzhen Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hong Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Guangxi Normal University, College of CS and IT, Guilin, China, and University of Technology, Faculty of Engineering and Information Technology, Sydney, Australia

    Shichao Zhang

  2. Department of Electrical and Computer Systems Engineering, Monash University, 3800, Melbourne, Victoria, Australia

    Ray Jarvis

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Liang, J., Jiang, H. (2005). BP Learning and Numerical Algorithm of Dynamic Systems. In: Zhang, S., Jarvis, R. (eds) AI 2005: Advances in Artificial Intelligence. AI 2005. Lecture Notes in Computer Science(), vol 3809. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11589990_109

Download citation

  • DOI: https://doi.org/10.1007/11589990_109

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-30462-3

  • Online ISBN: 978-3-540-31652-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation