Training multilayer perceptrons for control systems applications - a comparison of different approaches

Ruano, Antonio

http://hdl.handle.net/10400.1/2334

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
16.pdf		1.11 MB	Adobe PDF	Download

Send Feedback

Authors

Ruano, Antonio

Abstract(s)

Multilayer perceptrons (MLPs) (1) are the most common artificial neural networks employed in a large field of applications. In control and signal processing applications, MLPs are mainly used as nonlinear mapping approximators. The most common training algorithm used with MLPs is the error back-propagation (BP) alg. (1).

URI

http://hdl.handle.net/10400.1/2334

Citation

Ruano, A. E. Training multilayer perceptrons for control systems applications - a comparison of different approaches, Trabalho apresentado em Int. Conf. on Engineering Applications of Neural Networks (EANN’96), In Int. Conf. on Engineering Applications of Neural Networks (EANN’96), London, 1996.