Abstract
The paper interplays between plasticity processes of natural neural networks [9] and Self-Optimizing Neural Networks (SONNs) [7]. The natural neural networks (NNNs) have great possibility in adaptation to environment. The possibility to adapt is based on the chemical processes changing synaptic plasticity and adapting neural network topology during life. The described SONNs are able to adapt their topology to the given problem (i.e. artificial neural network environment) in the functionally similar way the natural neural networks do. The SONNs as well as the NNNs solve together the two essential problems: neural networks topology optimization and weights parameters computation for the given environment. The ontogenic SONNs development gradually adapts network topology specializing the network to the given problem. The fully automatic deterministic self-adapting mechanism of SONNs 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.
References
Duch, W., Korbicz, J., Rutkowski, L., Tadeusiewicz, R.(eds): Biocybernetics and Biomedical Engineering. Neural Networks, EXIT Warsaw 6, 257–566 (2000)
Dudek-Dyduch, E., Horzyk, A.: Analytical Synthesis of Neural Networks for Selected Classes of Problems. In: Bubnicki, Z., Grzech, A. (eds.) Knowlege Engineering and Experts Systems, OWPN Wroclaw, pp. 194–206 (2003)
Fiesler, E., Beale, R. (eds.): Handbook of Neural Computation, pp. B3–C1. IOP Publishing Ltd and Oxford University Press, Bristol & New York (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.) Advanced Computer Systems, INFORMA Szczecin, 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 Company, Heidelberg (2003)
Horzyk, A., Tadeusiewicz, R.: Self-Optimizing Neural Networks. In: Yin, F., Wang, J., Guo, C. (eds.) Advances in Neural Networks - ISNN 2004, pp. 150–155. Springer, Heidelberg (2004)
Horzyk, A.: Self-Optimizing Neural Networks as a New Computational Tool in Biomedicine. In: Proc. of SIIB 2004, preTEXt Cracow (2004)
Konturek, S.: Neurofizjology. Human Fizjology. AGAT PRINT Cracow, 9–126 (1992)
Mendyk, A., Horzyk, A., Jachowicz, R., Polak, S.: Development of new microemulsions systems using ontogenic neural networks. In: Proc. of SIIB 2004, preTEXt Cracow (2004)
Polak, S., Horzyk, A., Mendyk, A., Skowron, A., Brandys, J.: Perspective of use self-optimizing neural networks in pharmacy - modeling survival time of III-B and IV-th stage Non-Small Cell Lung Cancer patients. In: Proc. of SIIB 2004, preTEXt Cracow (2004)
Tadeusiewicz, R., Wszolek, W., Izworski, A., Wszolek, T.: Utilization of Artificial Intelligence Methods for Assistance in Interpretation of Acoustic Signals. In: Brambilla, G., Ianniello, C., Maffei, L. (eds.) Proc. of the 5-th European Conference on Noise Control Naples, pp. 276–282 (2003)
Tadeusiewicz, R., Ogiela, M.R.: Machine Perception and Automatic Understanding of Medical Visualization. In: Damczyk, M. (ed.) Automatic Image Processing in Production Process, pp. 39–48. Second Polish-German Seminar, CAMT, Wroclaw (2003)
Tadeusiewicz, R., Mikrut, Z.: Neural-Based Object Recognition Support - From Classical Preprocessing to Space-Variant Sensing. In: Heiss, M. (ed.) Proc. of the International ICSC/IFAC Symposium on Neural Computation NC 1998, pp. 463–468. ICSC Academic Press, Canada (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Horzyk, A., Tadeusiewicz, R. (2005). Comparison of Plasticity of Self-optimizing Neural Networks and Natural Neural Networks. In: Mira, J., Álvarez, J.R. (eds) Mechanisms, Symbols, and Models Underlying Cognition. IWINAC 2005. Lecture Notes in Computer Science, vol 3561. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11499220_17
Download citation
DOI: https://doi.org/10.1007/11499220_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26298-5
Online ISBN: 978-3-540-31672-5
eBook Packages: Computer ScienceComputer Science (R0)