Abstract
The paper is concentrated on two essential problems: neural networks topology optimization and weights parameters computation that are often solved separately. This paper describes new solution of solving both selected problems together. According to proposed methodology a special kind of multilayer ontogenic neural networks called Self-Optimizing Neural Networks (SONNs) can simultaneously develop its structure for given training data and compute all weights in the deterministic way based on some statistical computations that are incomparably faster then many other training methods. The described network optimization process (both structural and parametrical) finds out a good compromise between a minimal topology able to correctly classify training data and generalization capability of the neural network. The fully automatic self-adapting mechanism of SONN does not use any a priori configuration parameters and is free from different training problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Duch, W., Korbicz, J., Rutkowski, L., Tadeusiewicz, R.: Biocybernetics and Biomedical Engineering. Neural Networks. EXIT Warsaw 6, 257–566 (2000)
Fiesler, E., Beale, R. (eds.): Handbook of Neural Computation. IOP Publishing Ltd and Oxford University Press, Bristol, B3–C1 (1997)
Hellwig, Z.: Elements of Calculus of Probability and Mathematical Statistics PWN Warsaw, pp. 40–50 (1993)
Horzyk, A.: New Efficient Ontogenic Neural Networks for Classification Tasks. In: Soldek, J., Drobiazbiewicz, L. (eds.) INFORMA Szczecin. Advanced Computer Systems, pp. 466–473 (2003)
Horzyk, A.: New Ontogenic Neural Network Classificator Based on Probabilistic Reasoning. In: Rutkowski, L., Kacprzyk, J. (eds.) Advances in Soft Computing. Neural Networks and Soft Computing, pp. 188–193. Physica Verlag, Springer-Verlag Company, Heidelberg (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Horzyk, A., Tadeusiewicz, R. (2004). Self-Optimizing Neural Networks. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive