Comparing evolutionary hybrid systems for design and optimization of multilayer perceptron structure along training parameters

Castillo, Pedro; Merelo, J. J.; Arenas, M. G.; Romero, Gustavo

doi:10.1016/j.ins.2007.02.021

Cited by 27 publications

(20 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Advantages of 2LP are simplicity and high speed of classification [12], [15], [16]. Quick resetting and resource-saving by low CEP are believed to be reachable if 2LP is optimised by its hidden layer neuron number (HLNN) along with the training parameters [12], [17], [18]. The criterion of optimisation is minimisation of CEP, which depends on the training parameters.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

-The research is focused on optimising two-layer perceptron for generalised scaled object classification problem. The optimisation criterion is minimisation of inaccuracy. The inaccuracy depends on training parameters and hidden layer neuron number. After its statistics is accumulated, minimisation is executed by a numerical search. Perceptron is optimised additionally by extra training. As it is done, the classification error percentage does not exceed 3 % in case of the worst scale distortion.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This integer might be determined by R and B . But bonds between these three integers are implicit [17], [20], [21].…”

Section: Training Parametersmentioning

confidence: 99%

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Romanuke

2015

Information Technology and Management Science

View full text Add to dashboard Cite

show abstract

“…In particular, however, the speed is more than adequate for the applications we have used it (Araujo et al 2008;Castillo et al 2002Castillo et al , 2008Merelo-Guervós and CastilloValdivieso 2004;Castillo et al 2007, for instance), and the availability of auxiliary libraries in Perl and the speed with which development and experiment processing afterwards can be done more than compensates for its lack of speed. Running a profiling tool over the programs also helps to identify the bottlenecks, which can then be attacked by using different techniques or implementations in other languages.…”

Section: Fitness Classesmentioning

confidence: 99%

Algorithm::Evolutionary, a flexible Perl module for evolutionary computation

2009

View full text Add to dashboard Cite

This paper describes Algorithm::Evolutionary (A::E), a Perl module released under an open source license and designed for the exploration and exploitation of evolutionary algorithms. We describe the design decisions taken to enhance flexibility, how performance was improved by using several implementation tweaks, and what kind of design patterns were applied for its development. This work also tries to dispel the myth of low performance of scripting languages by comparing it with a state-of-the-art library (ECJ) written in Java. Besides, we are interested in assessing its efficiency in several possible evolutionary settings, finding out what kind of behavior we can expect, and what can be done to improve it. Applications already written using A::E are also described, along with how it can be used to create new operators. Finally, some conclusions are drawn from the design experience.

show abstract

“…Castillo et al [12] explored several methods that combine evolutionary algorithms and local search to optimize multilayer perceptrons. Authors explored a method that optimizes the architecture and initial weights of multilayer perceptrons, a search algorithm for training algorithm parameters, and finally, a co-evolutionary algorithm, that handles the architecture, the network's initial weights and the training algorithm parameters.…”

Section: Recent Applications Of Evolutionary Neural Network In Practicementioning

confidence: 99%

Engineering Evolutionary Intelligent Systems: Methodologies, Architectures and Reviews

Abraham

Groşan

2008

Engineering Evolutionary Intelligent Systems

View full text Add to dashboard Cite

Summary. Designing intelligent paradigms using evolutionary algorithms is getting popular due to their capabilities in handling several real world problems involving complexity, noisy environment, imprecision, uncertainty and vagueness. In this Chapter, we illustrate the various possibilities for designing intelligent systems using evolutionary algorithms and also present some of the generic evolutionary design architectures that has evolved during the last couple of decades. We also provide a review of some of the recent interesting evolutionary intelligent system frameworks reported in the literature.

show abstract

Comparing evolutionary hybrid systems for design and optimization of multilayer perceptron structure along training parameters

Cited by 27 publications

References 85 publications

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Optimal Training Parameters and Hidden Layer Neuron Number of Two-Layer Perceptron for Generalised Scaled Object Classification Problem

Algorithm::Evolutionary, a flexible Perl module for evolutionary computation

Engineering Evolutionary Intelligent Systems: Methodologies, Architectures and Reviews

Contact Info

Product

Resources

About