Zusammenfassung
Aufbau und Eigenschaften mehrschichtiger Perceptrons werden beschrieben. Theoretische Arbeiten bestätigen, daß die Architektur eines Netzes das erreichbare Ge-neralisierungsvermögen bestimmt. Ein biologisch motivierter Ansatz zur Topologie-Optimierung wird vorgestellt. Mit Hilfe genetischer Algorithmen werden die Netzgraphen einer Population miteinander gekreuzt (crossover) und geringfügig verändert (mutiert). Die damit erzielten Ergebnisse werden am Beispiel eines medizinischen Klassifikationsproblems vorgestellt und diskutiert. Ein Ausblick soll zukünftige Forschungsrichtungen zur Topologie-Optimierung aufzeigen und zu weiteren Arbeiten in diesem Gebiet motivieren.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Literatur
Cybenko G., 1988 : Continuous Valued Neural Networks with Two Hidden Layers Are Sufficient, Technical Report, Department of Computer Science, Tufts University, Medford, MA
Cybenko G., 1989 : Approximation by Superpositions of a Sigmoidal Function, Mathematics of Control, Signals and Systems, 2, pp. 303–314
Denker J., Schwartz D., Wittner B., Solla S., Howard R., Jackel L. and Hopfield, 1987Large Automatic Learning, Rule Extraction and Generalization, Complex systems, 1, pp. 877–922
Dodd N., 1990 : Optimization of Network Structure Using Genetic Techniques, Proc. of the Intern. Conf. on Neural Networks, Paris
Goldberg D., 1989 : Genetic Algorithms – in Search, Optimization and Machine Learning, Addison-Wesley
Harp S.A., Samad T. and Guha A., 1989 : Towards the Genetic Synthesis of Neural Networks, Proc. of the third Intern. Conf. on Genetic Algorithms (ICGA), pp. 360–369, San Mateo (CA)
Hartman E.J., Keeler J.D. and Kowalski J.M., 1990 : Layered Neural Networks with Gaus-sian Hidden Units As Universal Approximations, Neural Computation 2, pp. 210–215
Hornik K., Stinchcombe M. and White H., 1989 : Multilayer Feedforward Networks are Universal Approximators, Neural Networks, Vol. 2, pp. 359–366, Pergamon Press
Lapedes A. and Farber R., 1988 : How Neural Nets Work, Neural Information Processing Systems, D.Z. Anderson (Ed.), American Institute of Physics, New York, pp. 442–456
Lehar S. and Weaver J., 1987 : A Developmental Approach to Neural Network Design, Proc. of the IEEE Intern. Conf. on Neural Networks, Vol. I, pp. 97–104
Merrill J. and Port R., 1991 : Fractally Configured Neural Networks, Neural Networks, Vol. 4, pp.53–60
Miller G., Todd P.M. and Hegde S.U., 1989 : Designing Neural Networks Using Genetic Algorithms, Proc. of the third Intern. Conf. on Genetic Algorithms (ICGA), pp. 379–384, San Mateo (CA)
Minsky and Papert, 1969 : Perceptrons, MIT Press
Mjolsness E. and Sharp D.H., 1986 : A Prelimiary Analysis of Recursively Generated Networks, in Denker J. (Eds.): Neural Networks for Computing, Snowbird (Utah)
Mjolsness E., Sharp D.H. and Alpert B.K., 1987 : Recursively Generated Neural Networks, Proc. of the IEEE Intern. Conf. on Neural Networks, Vol. III, pp. 165–171
Mühlenbein H. and Kindermann J., 1989 : The Dynamics of Evolution and Learning — Towards Genetic Neural Networks, in Pfeifer et al. (Eds.): Connectionism in Perspective, Elsevier
Rumelhart D.E., Hinton G.E., Williams R.J., 1986 : Learning internal representations by error propagation, Parallel Distributed Processing: Explorations in the Microstructures of Cognition, Vol.I, MIT Press, pp. 318–362
Schiffmann W.H. and Mecklenburg K., 1990 : Genetic Generation of Backpropagation Trained Neural Networks, Proc. of Parallel Processing in Neural Systems and Computers (ICNC), Eckmiller R. et al. (Eds.), pp. 205–208, Elsevier
Schiffmann W.H., Joost M. and Werner R., 1991 : Performance Evaluation of Evolutionarily Created Neural Network Topologies, Proc. of Parallel Problem Solving from Nature, Schwefel H.P. and Maenner R. (Eds.), pp. 274–283, Lect. Notes in Computer Science, Springer
Schiffmann W.H., Joost M. and Werner R., 1992a : Optimierung des Backpropagation Algorithmus zum Training von Multilayer Perceptrons, Fachbericht Physik, 15/1992, Universität Koblenz
Schiffmann W.H., Joost M. and Werner R., 1992b :Synthesis and Performance Analysis of Multilayer Neural Network Architectures, Fachbericht Physik 16/1992, Universität Koblenz
Schiffmann W.H., Joost M. and Werner R., 1993 : Application of Genetic Algorithms to the Construction of Topologies for Multilayer Perceptrons, Intern. Conf. on Neural Networks and Genetic Algorithms ICNNGA ’93, to appear, Innsbruck 1993
Schwartz D.B., Samalam V.K., Solla S.A. and Denker J.S., 1990 : Exhaustive Learning, Neural Computation 2, pp. 371–382
Solla S.A., 1989 :Learning and Generalization in Layered Neural Networks: The Contiguity Problem, Neural Networks from Models to Applications, Personnaz L. and Dreyfus G. (Eds.), Paris, pp. 168–177
Weiss, G. : Combining neural and evolutionary learning: Aspects and approaches, Report FKI-132–90, Technische Universität München, 1990
Weiss, G. : Combining neural and evolutionary learning: Aspects and approaches, Report FKI-132–90, Technische Universität München, 1990
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schiffmann, W. (1993). Evolutionäres Design von neuronalen Netzen. In: Hofestädt, R., Krückeberg, F., Lengauer, T. (eds) Informatik in den Biowissenschaften. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78072-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-78072-1_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56456-0
Online ISBN: 978-3-642-78072-1
eBook Packages: Springer Book Archive