Abstract
Neural Networks (NN) are usually trained with gradient search algorithms. Alternative approaches like genetic algorithms (GA) have been proposed before with promising results. In this paper six different training algorithms for NN are compared — two of them based on GA. The algorithms were evaluated with data from practically relevant applications of the Siemens AG.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aktas, A et al.; Classification of Coarse Phonetic Categories in Continuous Speech: Statistical Classifiers vs. Temporal Flow Connectionist Network; Intern. Conf. on Acoustics, Speech, and Signal Processing; New Mexico 1990.
Heistermann, J.: A Parallel Hybrid Learning Approach to Artificial Neural Nets; Proceedings of the third IEEE Symposium on Parallel and Distri-buted Processing; Dallas 1991.
Mühlenbein,H.; Kindermann, J.: The dynamics of evolution and learning — towards genetic neural networks; in Pfeifer, R., Schreter, Z., Fogelman-Soulie, F., Steels, L. (Eds.): Connectionism in perspective; Elsevier 1989.
Nijhuis, J.A.G.; Spaanenburg, L.: NNSIM Internal Structure Reference Version 3.0; Technical Report IMS-TB-07/89; Institut für Mikroelektronik (IMS) Stuttgart 1989.
Press, W.H.; Flannery, B.P.; Teukolsky, S.A.; Vetterling, W.T.: Numerical Recipes in C; Cambridge University Press New York 1988.
Rumelhart, D.E.; Hinton, G.E.; Williams, R.J.: Learning Internal Repre-sentations by Error Propagation; in Rumelhart, D.E.; McCLelland, J.L. (Eds.): Parallel Distributed Processing Vol.1; MIT Press Cambridge Massachusetts 1986.
Schwefel,H.-P.: Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie; Birkhäuser Basel und Stuttgart 1977.
Troll, A.: Optimierungsverfahren für die Lernphase bei Neuronalen Netzen; Diplomarbeit an der LMU München, Fachbereich Mathmatik; München 1991.
Whitley, D., Bogart, C.: The evolution of connectivity: Pruning neural networks using genetic algorithms; Proc. of the 3rd Intern. Joint Conf. on Neural Networks 1989.
Whitley, D., Hanson, T.: Optimizing neural networks using faster, more accurate genetic search; Proc. of the 3rd Intern. Conf. on Genetic Algorithms 1989.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Heistermann, J. (1994). Different learning algorithms for Neural Networks — A comparative study. 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_282
Download citation
DOI: https://doi.org/10.1007/3-540-58484-6_282
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