Cooperative Co-evolution of Multilayer Perceptrons

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

doi:10.1007/3-540-44868-3_46

Cited by 10 publications

(17 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The complete description of the method and the results obtained using classification problems have been presented elsewhere [6], [7], [8], [9]. The designed method uses an elitist algorithm [29].…”

Section: The Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary system for prediction and optimization of hardware architecture performance

Castillo

Merelo

Moretó

et al. 2008

2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence)

Self Cite

View full text Add to dashboard Cite

Abstract-The design of computer architectures is a very complex problem. The multiple parameters make the number of possible combinations extremely high. Many researchers have used simulation, although it is a slow solution since evaluating a single point of the search space can take hours. In this work we propose using evolutionary multilayer perceptron (MLP) to compute the performance of an architecture parameter settings. Instead of exploring the search space, simulating many configurations, our method randomly selects some architecture configurations; those are simulated to obtain their performance, and then an artificial neural network is trained to predict the remaining configurations performance. Results obtained show a high accuracy of the estimations using a simple method to select the configurations we have to simulate to optimize the MLP. In order to explore the search space, we have designed a genetic algorithm that uses the MLP as fitness function to find the niche where the best architecture configurations (those with higher performance) are located. Our models need only a small fraction of the design space, obtaining small errors and reducing required simulation by two orders of magnitude.

show abstract

Section: The Methodsmentioning

confidence: 99%

“…We propose to focus the effort on the ANN optimization using GProp [6], [7], [8], [9], an evolutionary method for the design and optimization of neural networks.…”

Section: Introductionmentioning

confidence: 99%

Evolutionary system for prediction and optimization of hardware architecture performance

Castillo

Merelo

Moretó

et al. 2008

2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A given fully connected FNN may become a partially connected network after learning. The GA equipped with the backpropagation (BP) [135] can be used to train both the architecture and the weights of the multilayer perceptron [128,136,137]. In [128], the Quickprop algorithm [138] is used to tune a solution and to reach the nearest local minimum from the solution found by the GA.…”

Section: Simultaneously Evolving Architecture and Parametersmentioning

confidence: 99%

“…This strategy avoids Lamarckism. The GProp method [136] is modified in [137] by integrating the Quickprop as a training operator, as performed in [128]. This method, thus, implements the Lamarckian evolution.…”

Section: Simultaneously Evolving Architecture and Parametersmentioning

confidence: 99%

Evolutionary Computation and Its Applications in Neural and Fuzzy Systems

Zhang¹,

Wu²,

et al. 2011

Applied Computational Intelligence and Soft Computing

View full text Add to dashboard Cite

Neural networks and fuzzy systems are two soft-computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general-purpose stochastic global optimization approach under the universally accepted neoDarwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed.

show abstract

“…A peculiar aspect is that BP is not used as some genetic operator, as it is the case in some related work [1]. Instead, the EA optimizes both the topology and the weights of the networks; BP is optionally used to decode a genotype into a phenotype NN.…”

Section: Neuro-genetic Approachmentioning

confidence: 99%

A neural evolutionary approach to financial modeling

Azzini

Tettamanzi

2006

Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

This paper presents an approach to the joint optimization of neural network structure and weights which can take advantage of backpropagation as a specialized decoder. The approach has been applied to a financial problem, whereby a factor model capturing the mutual relationships among several financial instruments is sought for. A sample application of such a model to statistical arbitrage is also presented.

show abstract

Cooperative Co-evolution of Multilayer Perceptrons

Cited by 10 publications

References 13 publications

Evolutionary system for prediction and optimization of hardware architecture performance

Evolutionary system for prediction and optimization of hardware architecture performance

Evolutionary Computation and Its Applications in Neural and Fuzzy Systems

A neural evolutionary approach to financial modeling

Contact Info

Product

Resources

About