Abstract
Kitano proposed to use GA with graph encoding method to have good scalability for hierarchical networks. However, this is not applicable to recurrent networks. The authors propose to use a combination of a structural learning with forgetting(SLF) and GA for designing recurrent neural networks; the former generates quasi-optimal recurrent network structure and the latter prevents local minima by global search. Its applications to two kinds of time series data well demonstrate the superiority to SLF and to a combination of GA and BPTT.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
Akaike, II.: A new look at the statistical model identification, IEEE Trans. on AC 19-6 (1974) 716–723
Box, G. E. P., Jenkins, G. M.: Time Series Analysis forecasting and control, HoldenDay (1976) 370–418
Ishikawa, M.: Structural learning and knowledge acquisition, IEEE ICNN'96 (1996) Washington D.C., 100–105
Ishikawa, M.: Structural learning with forgetting, Neural Networks 9-3 (1996) 509–521
Kitano, H.: Designing Neural Networks Using Genetic Algorithms with Graph Generation System, Complex Systems 4 (1990) 461–476
Kitano, H.: Neurogenetic Learning: an Integrated Method of Designing and Training Neural Networks Using Genetic Algorithms, Physica D 75 (1994) 225–238
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ishikawa, M., Nishino, K. (1997). Designing neural networks by a combination of structural learning and genetic algorithms. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020190
Download citation
DOI: https://doi.org/10.1007/BFb0020190
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive