Abstract
The gradient based learning algorithms for complex hybrid neurofuzzy architectures have a lot of local minima and a seriously time consumption complexity is involved as a consequence. Genetic Algorithms with variable length genotypes are successfully used in getting better performances for systems with complex structure or, at the same performances, a less complex structure of the system. We propose a sophisticated algorithm that solves simultaneously the optimization objectives of learning algorithms in fuzzy recurrent neural networks: both regarding the fuzzy NN performances (by its fuzzy weights matrix) and regarding the architecture (number of fully connected neurons). In this paper we developed a genetic algorithm with variable length genotypes that offers a systematic way of getting a minimal neuro-fuzzy structure satisfying the above mentioned requested performance. This advantage is not to be neglected when a complex hybrid intelligent architecture must be designed without any previous details regarding it requested architecture.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arotaritei, D.: Dynamic Adapted Gradient Algorithm for Hybrid Recurrent Structure. Word Multiconference on Systemics, Cybernetics and Informatics ISAS/SCI 2001, Orlando, Florida, USA (2001) 568–571
Coello, C.A.: A Survey of Constraint Handling Techniques used with Evolutionary Algorithms. Lania-RI-99-04, Laboratorio Nacional de Informática Avanzada (1999)
Fagarasan, F., Negoita, Gh. M.: Genetic Based Method for Learning the Parameters of a Fuzzy Inference System, Proceedings of ANNES’95, Dunedin, Otago, New Zealand (1995) 223–226
Harvey, I.: Species Adaptation Genetic Algorithms: a basis for a continuing SAGA, Proceedings of the First European Conference on Artificial Life. Toward a Practice of Autonomous Systems, MIT Press, Cambridge, York (1991) 346–354
Kandel, A., Teodorescu, H.N., Arotaritei, D.: Analytic Fuzzy RBF Neural Network. Proceedings of the 17th Annual Meeting of the North American Fuzzy Information Processing Society NAFIPS’98, Pensacola Beach, Florida, USA (1998)
Teodorescu, H.N.: Non-Linear Systems, Fuzzy Systems, and Neural Networks. Proc. 3rd Int.Conference on Fuzzy Logic, Neural Nets and Soft Comp. (1994) 17–28
Williams, R.J., Zipser, D.: Experimental Analysis of the Real-time Recurrent Learning Algorithm. Connection Science, Vol. 1, No. 1 (1989) 87–111
Zimmerman, H.-J., Negoita, Gh. M, Dascalu, D., (Eds): Real World Application of Intelligent Technologies, Editura Academiei Romane (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Arotaritei, D., Negoita, M.G. (2002). Optimization of Recurrent NN by GA with Variable Length Genotype. In: McKay, B., Slaney, J. (eds) AI 2002: Advances in Artificial Intelligence. AI 2002. Lecture Notes in Computer Science(), vol 2557. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36187-1_60
Download citation
DOI: https://doi.org/10.1007/3-540-36187-1_60
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00197-3
Online ISBN: 978-3-540-36187-9
eBook Packages: Springer Book Archive