Abstract
This paper describes an efficient construction of a partially-connected multilayer architecture and a computation of weight parameters of Self-Optimizing Neural Network 3 (SONN-3) that can be used as a universal classifier for various real, integer or binary input data, even for highly non-separable data. The SONN-3 consists of three types of neurons that play an important role in a process of extraction and transformation of important features of input data in order to achieve correct classification results. This method is able to collect and to appropriately reinforce values of the most important input features so that achieved generalization results can compete with results achieved by other existing classification methods. The most important aspect of this method is that it neither loses nor rounds off any important values of input features during this computation and propagation of partial results through a neural network, so the computed classification results are very exact and accurate. All the most important features and their most distinguishing ranges of values are effectively compressed and transformed into an appropriate network architecture with weight values. The automatic construction process of this method and all optimization algorithms are described here in detail. Classification and generalization results are compared by means of some examples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Duch, W., Korbicz, J., Rutkowski, L., Tadeusiewicz, R. (eds.): Biocybernetics and Biomedical Engineering. EXIT, Warszawa (2000)
Dudek-Dyduch, E., Horzyk, A.: Analytical Synthesis of Neural Networks for Selected Classes of Problems. In: Bubnicki, Z., Grzech, A. (eds.) Knowledge Engineering and Experts Systems, OWPN, Wroclaw, pp. 194–206 (2003)
Fiesler, E., Beale, R. (eds.): Handbook of Neural Computation. IOP Publishing Ltd., Oxford University Press, Bristol, New York (1997)
Horzyk, A.: Introduction to Constructive and Optimization Aspects of SONN-3. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008,, Part II. LNCS, vol. 5164, pp. 763–772. Springer, Heidelberg (2008)
Horzyk, A.: A New Extension of Self-Optimizing Neural Networks for architecture Optimization. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 415–420. Springer, Heidelberg (2005)
Horzyk, A., Tadeusiewicz, R.: Comparison of Plasticity of Self-Optimizing Neural Networks and Natural Neural Networks. In: Mira, J., Alvarez, J.R. (eds.) Proc. of ICANN 2005, pp. 156–165. Springer, Heidelberg (2005)
Hyvarinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. John Wiley and Sons, Chichester (2001)
Jankowski, N.: Ontogenic neural networks. EXIT, Warszawa (2003)
Jolliffe, I.T.: Principal Component Analysis. Springer, Heidelberg (2002)
Kalat, J.: Biological Psychology, Thomson Learning Inc. Thomson Learning Inc., Wadsworth (2004)
Pawlak, Z.: Rough sets. In: Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers, Dordrecht (1991)
Starzyk, J.A.: Motivation in Embodied Intelligence, Robotics, Automation and Control. I-Tech Education and Publishing (2008)
Subirats, J.L., Franco, L., Molina Conde, I., Jerez, J.M.: Active Learning Using a Constructive Neural Network Algorithm. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008,, Part II. LNCS, vol. 5164, pp. 803–811. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Horzyk, A. (2009). Self-Optimizing Neural Network 3. In: Franco, L., Elizondo, D.A., Jerez, J.M. (eds) Constructive Neural Networks. Studies in Computational Intelligence, vol 258. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04512-7_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-04512-7_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04511-0
Online ISBN: 978-3-642-04512-7
eBook Packages: EngineeringEngineering (R0)