Abstract
The purpose of this article is to make a contribution to the study of modular structure of neural nets, in particular to describe a method of automatic neural net modularization. The problem specific modularizations of the representation emerge through the iterations of the evolutionary algorithm directly with the problem. We used the probability vector to construct n – bit vectors, which represented individuals in the population (in our approach they describe an architecture of a neural network). All individuals in every generation are pseudorandomly generated from the probability vector that is associated with this generation. The probability vector is updated on the basis of best individuals in a population, so that next generations are getting progressively closer to best solutions. The process is repeated until the probability vector entries are close to zero or to one. The resulting probability vector then determines an optimal solution of the given optimization task.
Keywords
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
Volna, E.: Neural structure as a modular developmental system. In: Sinčák, P., Vaščák, J., Kvasnička, V., Pospíchal, J. (eds.) Intelligent technologies – theory and applications, pp. 55–60. IOS Press, Amsterdam (2002)
Fausett, L.V.: Fundamentals of neural networks. Prentice-Hall, Inc., Englewood Cliffs, New Jersey (1994)
Rueckl, J.G.: Why are “What” and “Where” processed by separate cortical visual systems? A computational investigation. Journal of Cognitive Neuroscience 2, 171–186 (1989)
Anděl, J.: Matematická statistika. I. vydání. SNTL Praha (in Czech) (1978)
Kvasnička, V., Pelikán, M., Pospíchal, J.: Hill climbing with learning (an abstraction of genetic algorithm). Neural network world 5, 773–796 (1996)
Goldberg, D.E.: Genetic algorithm in search optimalization and machine learning. Addison-Wesley, Reading, Massachusets (1989)
Rektorys, K.: Přehled užité matematiky. SNTL Praha (in Czech) (1981)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Volna, E. (2007). Designing Modular Artificial Neural Network Through Evolution. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4668. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74690-4_31
Download citation
DOI: https://doi.org/10.1007/978-3-540-74690-4_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74689-8
Online ISBN: 978-3-540-74690-4
eBook Packages: Computer ScienceComputer Science (R0)