Speeding up a learning algorithm for multilayer perceptrons using the MAPS Environment

Daniel, H. A.; Ruano, Antonio

http://hdl.handle.net/10400.1/2288

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
chair_get_file_doc_id=38&ession_id=14.pdf		210.98 KB	Adobe PDF	Download

Send Feedback

Authors

Daniel, H. A.

Ruano, Antonio

Abstract(s)

Artificial neural networks, as non-linear adaptive elements, have been proposed for applications in adaptive control. Their ability to accurately approximate large classes of non-linear functions made them also a valuable tool for non-linear systems identification. However, in some cases, the parameter estimation phase may take considerable amount of time, and this is crucial in real-time applications. One way of speeding up these learning algorithms consists in executing them over a multiprocessor system. In this paper an implementation over MAPS integrated development environment, which automatically generates a parallel application from a sequential description of a learning algorithm for multilayer perceptrons is presented.

Keywords

Multiprogramming Neural Networks Parallel Algorithms Multiprocessing Systems Digital Signal Processors

URI

http://hdl.handle.net/10400.1/2288

Citation

Daniel, H.; Ruano, A. E. Speeding up a Learning Algorithm for Multilayer Perceptrons using the MAPS Environment, Trabalho apresentado em 6th Portuguese Conference on Automatic Control (Controlo 2004), In 6th Portuguese Conference on Automatic Control (Controlo 2004), Faro, 2004.