Abstract
The simultaneous topology optimization and training of neu- ral networks is a problem widely studied in the last years, specially for feedforward models. In the case of recurrent neural networks, the existing proposals attempt to only optimize the number of hidden units, since the problem of topology optimization is more difficult due to the feedback connections in the network structure. In this work, we make a study of the effects and difficulties for the optimization of network connections, hidden neurons and network training for dynamical recurrent models. In the experimental section , the proposal is tested in time series prediction problems.
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.
References
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice-Hall, Englewood Cliffs (1999)
Giles, C.L., Chen, D., Sun, G.Z., Chen, H., Lee, Y.C., Goudreau, M.W.: Constructive learning of recurrent neural networks: problems with recurrent cascade correlation and a simple solution. IEEE Transactions on Neural Networks 6(4), 829 (1995)
Yao, X.: Evolving artificial neural networks. Proc. of the IEEE 87(9), 1423–1447 (1999)
Jin, Y.: Multi-objective machine learning. Springer, New York (2006)
Mandic, D.P., Chambers, J.: Recurrent Neural Networks for Prediction. John Wiley and sons, Chichester (2001)
Teo, J., Abbass, H.A.: Information-theoretic landscape analysis of neuro-controlled embodied organisms. Neural Computing and Applications 31(1), 80–89 (2004)
Teo, J., Abbass, H.A.: Multi-objectivity and complexity in embodied cognition. IEEE Trans. on Evolutionary Computation 9(4), 337–370 (2005)
Cuéllar, M.P., Delgado, M., Pegalajar, M.C.: Multiobjetive evolutionary optimization for elman recurrent neural networks, applied to time series prediction. Fuzzy Economical Review X(1), 165–181 (2005)
Delgado, M., Pegalajar, M.C.: A multiobjective genetic algorithm for obtaining the optimal size of a recurrent neural network for grammatical inference. Pattern Recognition 38(9), 1444–1456 (2005)
Zitzler, E., Laumanns, M., Thiele, L.: Spea2: Improving the strength pareto evolutionary algorithm. Technical Report 103, Computer Engineering and Networks Laboratory (TIK), Swiss Federal Institute of Technology (ETH), Zurich, Switzerland (May 2001)
Deb, K., Pratap, A., Agarwal, A., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE Transactions on Evolutionary Computation 6(2), 182–197 (2002)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cuéllar, M.P., Delgado, M., Pegalajar, M.C. (2007). Topology Optimization and Training of Recurrent Neural Networks with Pareto-Based Multi-objective Algorithms: A Experimental Study. In: Sandoval, F., Prieto, A., Cabestany, J., Graña, M. (eds) Computational and Ambient Intelligence. IWANN 2007. Lecture Notes in Computer Science, vol 4507. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73007-1_44
Download citation
DOI: https://doi.org/10.1007/978-3-540-73007-1_44
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73006-4
Online ISBN: 978-3-540-73007-1
eBook Packages: Computer ScienceComputer Science (R0)