Abstract
We present a novel approach for the structuring of artificial neural networks by an Evolutionary Algorithm. The structuring problem is discussed as an example of a pseudo-boolean optimization problem. The continuous Evolution Strategy is extended by an individual developmental process, in our case a stochastic generation scheme, to allow the use of adaptive genetic operators. On exemplary tests we analyze the performance and evaluate the efficiency of this approach.
Supported by the Bundesministerium für Forschung und Technologie (BMFT) grant SALGON (No. 01 IN 107).
Preview
Unable to display preview. Download preview PDF.
References
S. E. Fahlman, C. Lebiere. The Cascade-Corellation Learning Architecture. In D.S. Touretzky (ed.): Advances in Neural Information Pressing Systems 2. Morgan Kaufmann. 1990.
K. J. Lang, M. J. Witbrock. Learning to Tell Two Spirals Apart. In D.S. Touretzky et al. (eds.), Proceedings of the 1988 Connectionist Models Summer School. Morgan Kaufmann. 1988.
H. Kitano. Designing neural networks using genetic algorithm with graph generation system. Complex Systems, 4:461–476, 1990.
I. Rechenberg. Evolutionsstrategie: Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Frommann-Holzboog, Stuttgart. 1973.
I. Rechenberg. Evolutionsstrategie '94. Frommann-Holzboog, Stuttgart. 1994. (In press.)
D. E. Rumelhart, J. L. McClelland. Parallel Distributed Processing. Explorations in the Micro-structure of Cognition. Cambridge, Massachusetts, The MIT Press. 1986.
H.P. Schwefel. Numerical Optimization of Computer Models. J. Wiley, Chichester, New York, Brisbane, Toronto. 1981.
H. Spielberg. Bushhouse — The documentation to the C — code of the BBC-EA. Internal report, Technical University Berlin, Bionics and Evolution Techniques Laboratory, 1993.
H.-M. Voigt, J. Born, I. Santibáñez-Koref. Structuring of Artificial Neural Networks with Generative Grammars. In: M. v.d. Meer (Ed.): Statusseminar des BMFT Neuroinformatik 1992, pages 45–54. DLR, Berlin, 1992.
H.-M. Voigt and J. Born and I. Santibáñez-Koref. Evolutionary Structuring of Artifical Neural Networks, Technical Report TR-93-002, Technical University Berlin, Bionics and Evolution Techniques Laboratory, 1993.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Born, J., Santibáñez-Koref, I., Voigt, H.M. (1994). Designing neural networks by adaptively building blocks in cascades. In: Davidor, Y., Schwefel, HP., Männer, R. (eds) Parallel Problem Solving from Nature — PPSN III. PPSN 1994. Lecture Notes in Computer Science, vol 866. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58484-6_290
Download citation
DOI: https://doi.org/10.1007/3-540-58484-6_290
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58484-1
Online ISBN: 978-3-540-49001-2
eBook Packages: Springer Book Archive