Single and multi-objective genetic programming design for B-spline neural networks and neuro-fuzzy systems

Cabrita, Cristiano Lourenço; Ruano, Antonio; Fonseca, C. M.

http://hdl.handle.net/10400.1/2211

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
paper_aruano.pdf		242.67 KB	Adobe PDF	Download

Send Feedback

Authors

Cabrita, Cristiano Lourenço

Ruano, Antonio

Fonseca, C. M.

Abstract(s)

The design phase of B-spline neural networks and neuro-fuzzy systems is a highly computationally complex task. Existent heuristics, namely the ASMOD algorithm, have been found to be highly dependent on the initial conditions employed. A Genetic Programming approach is proposed, which produces an efficient topology search, obtaining additionally more consistent solutions. The facility to incorporate a multi-objective approach to the GP algorithm is exploited, enabling the designer to obtain better conditioned models, and more adequate for their intended use.

Keywords

Constructive algorithms B-Splines Neuro-fuzzy systems Genetic programming Single and multi-objective optimization

URI

http://hdl.handle.net/10400.1/2211

Citation

Cabrita, C.; Ruano, A. E.; Fonseca, C. M. Single and Multi-Objective Genetic Programming Design for B-Spline Neural Networks and Neuro-Fuzzy Systems, Trabalho apresentado em IFAC Workshop on Advanced Fuzzy-Neural Control (AFNC' 01), In IFAC Workshop on Advanced Fuzzy-Neural Control (AFNC' 01), Valencia, 2001.