An hybrid training method for B-spline neural networks

Cabrita, Cristiano Lourenço; Botzheim, J.; Ruano, Antonio; Kóczy, László T.

http://hdl.handle.net/10400.1/2235

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
cabrita 2005.pdf		1.32 MB	Adobe PDF	Download

Send Feedback

Authors

Cabrita, Cristiano Lourenço

Botzheim, J.

Ruano, Antonio

Kóczy, László T.

Abstract(s)

Current and past research has brought up new views related to the optimization of neural networks. For a fixed structure, second order methods are seen as the most promising. From previous works we have shown how second order methods are of easy applicability to a neural network. Namely, we have proved how the Levenberg-Marquard possesses not only better convergence but how it can assure the convergence to a local minima. However, as any gradient-based method, the results obtained depend on the startup point. In this work, a reformulated Evolutionary algorithm - the Bacterial Programming for Levenberg-Marquardt is proposed, as an heuristic which can be used to determine the most suitable starting points, therefore achieving, in most cases, the global optimum.

Keywords

Levenberg-Marquard algorithm B-Splines Genetic Programming Bacterial Algorithm Local and global minima

URI

http://hdl.handle.net/10400.1/2235

Citation

Cabrita, C.; Botzheim, J.; Ruano, A. E. B.; Koczy, L.T. An hybrid training method for B-spline neural networks, Trabalho apresentado em IEEE International Workshop on Intelligent Signal Processing, 2005. In Proceedings of the IEEE International Workshop on Intelligent Signal Processing, 2005. University of Algarve Portugal, 2005.