Skip to main content

An on-line learning algorithm for the orthogonal weight estimation of MLP

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

We propose an on-line learning algorithm for Multi Layered Perceptrons (MLP) with an Orthogonal Weight Estimator (OWE) architecture. Such an architecture allows to dynamically and efficiently estimate the weights of a MLP in context dependent behaviour problems. The proposed learning algorithm attempts to solve the problem of time-consuming in the learning phase encountered to train these weight estimators.

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

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. N. Pican, F. Alexandre. Integration of context in process models used for neuro-control,IEEE SMC'93 Conferenc,. Le Touquet (France), October 17–20, 1993.

  2. N. Pican, J.C. Fort, F. Alexandre. Lateral contribution learning algorithm for multi-MLP architecture,Proc. ESANN'94 (Brussels, Belgium), April 20–22, pp. 229–234, 1994.

  3. J. Buhmann, H. Kuhnel. Complexity optimized vector quantization: a neural network approach,Proc. Data Compression Conference (Snowbird), March 24–27, 1992.

  4. J. Buhmann, H. Kuhnel. Unsupervized and supervised data clustering with competitive neural networks,Proc. IJCNN'92 (Baltimore), IEEE Press, 1992.

  5. Y. LeCun. Procédure d'apprentissage pour réseaux à seuil asymétrique,Proc. Cognitiva 1985 (Paris), 1985.

  6. D.E. Rumelhart, G.E. Hinton, R.J. Williams. Learning internal representations by error propagation, in:Parallel Distributed Processing: Explorations in the Microstructures of Cognition, MIT Press, vol. 1, pp. 318–362, 1986.

  7. H.J. Kushner, D.S. Clarck. Stochastic approximation for constrained and unconstrained systems,Applied Math. Science Series, Springer, n. 26, 1978.

  8. F. M. Silva, L. B. Almeidia,. Speeding up backpropagation, in:Advanced Neural Computers, R. Eckmiller R. ed., pp. 151–158, 1990.

  9. N. Pican, F. Alexandre. Highly adaptive neural network for adaptive neuro-controller: OWE architecture,Proc. IEEE SMC'94 (San Antonio, Texas), October 2–5, 1994

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pican, N., Fort, JC. & Alexandre, F. An on-line learning algorithm for the orthogonal weight estimation of MLP. Neural Process Lett 1, 21–24 (1994). https://doi.org/10.1007/BF02312397

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02312397

Keywords