Abstract
For many applications feedforward neural networks have proved to be a valuable tool. Although the basic principles of employing such networks are quite straightforward, the problem of tuning their architectures to achieve near optimal performance still remains a very challenging task. Genetic algorithms may be used to solve this problem, since they have a number of distinct features that are useful in this context. First, the approach is quite universal and can be applied to many different types of neural networks or training criteria. It also allows network topologies to be optimized at various level of detail and can be used with many types of energy function, even those that are discontinuous or non-differentiable. Finally, a genetic algorithm need not be limited to simply adjusting patterns of connections, but, for example, can be utilized to select node transfer functions, weight values or to find architectures that perform best under certain simulated working conditions. In this paper we have investigated an application of genetic algorithms to feedforward neural network architecture design. These neural networks are used to model a nonlinear, discrete SISO system when only noisy training data are available. Additionally, some incidental but nonetheless important aspects of neural network optimization, such as complexity penalties or automatic topology simplification are discussed.
Preview
Unable to display preview. Download preview PDF.
References
ästrom K. I., Wittenmark B., Computer Controlled Systems — Theory and Design, Prentice-Hall, 1984.
Bäck T., Hoffmeister F., Extended Selection Mechanisms in Genetic Algorithms, Proc. 4th Int. Conf. on Genetic Algorithms, Morgan Kaufmann, 1991.
Billings S.A., Zhu Q.M., Nonlinear model validation using correlation tests, Int. J. Control, 1994, vol. 60, no. 6, pp. 1107–1120.
Billings S.A., Jamaluddin H.B., Chen S., Properties of neural networks with applications to modeling non-linear dynamical systems, Int. J. Control, 1992, vol. 55, no. 1, pp. 193–224.
Goldberg D. E., Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989.
Haykin S., Neural Networks — A Comprehensive Foundation, Macmillan College Publishing, 1994.
Kitano, H., Neurogenetic learning: an integrated method of designing and training neural networks using genetic algorithms, Physica D 75, 1994, pp. 225–238.
Keane A.J., The Options Design Exploration System, Reference Manual and User Guide, 1994, available at http://www.eng.ox.ac.uk/people/Andy.Keane/.
Kuscu I., Thornton C., Design of Artificial Neural Networks Using Genetic Algorithms: review and prospect, Cognitive and Computing Sciences, University of Sussex, 1994.
Schiffmann W., Joost M., Werner R., Optimization of the Backpropagation Algorithm for Training Multilayer Perceptrons, Technical Report, University of Koblenz, 1992.
Stepniewski S.W., Keane A.J., Pruning backpropagation neural networks using modern stochastic optimization techniques, (accepted for publishing by Neural Computing & Applications).
Whitley D., Starkweather T., Bogart C., Genetic Algorithms and Neural Networks: optimizing connections and connectivity, Parallel Computing 14, 1990, pp. 347–361.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stepniewski, S.W., Keane, A.J. (1996). Topology design of feedforward neural networks by genetic algorithms. In: Voigt, HM., Ebeling, W., Rechenberg, I., Schwefel, HP. (eds) Parallel Problem Solving from Nature — PPSN IV. PPSN 1996. Lecture Notes in Computer Science, vol 1141. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61723-X_1040
Download citation
DOI: https://doi.org/10.1007/3-540-61723-X_1040
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61723-5
Online ISBN: 978-3-540-70668-7
eBook Packages: Springer Book Archive