Optimisation of Multilayer Perceptrons Using a Distributed Evolutionary Algorithm with SOAP

SOAP (simple object access protocol) is a protocol that allows the access to remote objects independently of the computer architecture and the language. A client using SOAP can send or receive objects, or access remote object methods. Unlike other remote procedure call methods, like XML-RPC or RMI, SOAP can use many different transport types (for instance, it could be called as a CGI or as sockets). In this paper an approach to evolutionary distributed optimisation of multilayer perceptrons (MLP) using SOAP and language Perl has been done.Obtained results show that the parallel version of the developed programs obtains similar or better results using much less time than the sequential version, obtaining a good speedup. Also it can be shown that obtained results are better than those obtained by other authors using different methods.

[1]  John J. Grefenstette,et al.  A Parallel Genetic Algorithm , 1987, ICGA.

[2]  David Abramson,et al.  A PARALLEL GENETIC ALGORITHM FOR SOLVING THE SCHOOL TIMETABLING PROBLEM , 1992 .

[3]  大島 正嗣,et al.  Simple Object Access Protocol と,その応用としてのソフトウェアの組み合わせについて (渡邉昭夫教授退任記念号) , 2001 .

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  Elliotte Rusty Harold.  XML Bible , 1999 .

[6]  Erik T. Ray.  Learning XML - creating self-describing data , 2001 .

[7]  Marko Gronroos,et al.  Evolutionary Design of Neural Networks , 1998 .

[8]  Lutz Prechelt,et al.  PROBEN 1 - a set of benchmarks and benchmarking rules for neural network training algorithms , 1994 .

[9]  Scott E. Fahlman,et al.  An empirical study of learning speed in back-propagation networks , 1988 .

[10]  Juan Julián Merelo Guervós,et al.  Evolving Multilayer Perceptrons , 2000, Neural Processing Letters.

[11]  Erick Cantú-Paz,et al.  Modeling Idealized Bounding Cases of Parallel Genetic Algorithms , 1996 .

[12]  L. Darrell Whitley,et al.  The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best , 1989, ICGA.

[13]  J. Roy,et al.  Understanding Web services , 2001 .

[14]  Juan Julián Merelo Guervós,et al.  G-Prop: Global optimization of multilayer perceptrons using GAs , 2000, Neurocomputing.

[15]  Reiko Tanese,et al.  Parallel Genetic Algorithms for a Hypercube , 1987, ICGA.

[16]  Maarten Keijzer,et al.  Evolving Objects: A General Purpose Evolutionary Computation Library , 2001, Artificial Evolution.

[17]  Reinhard Männer,et al.  Implementation of Standard Genetic Algorithm on MIMD Machines , 1994, PPSN.

[18]  Runhe Huang,et al.  Implementing the Genetic Algorithm on Transputer Based Parallel Processing Systems , 1990, PPSN.

[19]  Pedro A. Castillo,et al.  Jeo: a framework for evolving objects in java , 2001 .

[20]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[21]  D. Box,et al.  Simple Object Access Protocol (SOAP) 1.1, W3C Note , 2000 .