G-Prop: Global optimization of multilayer perceptrons using GAs

Castillo, Pedro; Merelo, J. J.; Prieto, Alberto; Rivas, Víctor M.; Romero, Gustavo

doi:10.1016/s0925-2312(00)00302-7

Cited by 134 publications

(67 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After only 5 iterations, and in less than 1 s, the number of misclassiÿed cases dropped to 2, which corresponds to an error of only 3.3%. Table 4 compares these results with that obtained by other authors [6]. We can see that H-LVQ outperforms other methods, including simulated annealing.…”

Section: Application To Dna Helicasesmentioning

confidence: 59%

A training algorithm for classification of high-dimensional data

Vieira¹,

Barradas

2003

Neurocomputing

View full text Add to dashboard Cite

We propose an algorithm for training multi layer preceptrons (MLP) for classiÿcation problems, that we named hidden layer learning vector quantization. It consists of applying learning vector quantization to the last hidden layer of a MLP and it gave very successful results on problems containing a large number of correlated inputs. It was applied with excellent results on classiÿcation of Rutherford backscattering spectra and to a benchmark problem of image recognition.

show abstract

Section: Application To Dna Helicasesmentioning

confidence: 59%

A training algorithm for classification of high-dimensional data

Vieira¹,

Barradas

2003

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…This paper continues the research on evolutionary optimization of multilayer perceptrons (MLPs) (G-Prop method) presented in [3,5], comparing several hybrid systems to optimize MLPs. The G-Prop method leverages the capabilities of two classes of algorithms: the ability of EA to find a solution close to the global optimum, and the ability of the back-propagation algorithm (BP) to tune a solution and reach the nearest local minimum by means of local search from the solution found by the EA.…”

Section: Introductionmentioning

confidence: 71%

“…We can see how the classification ability improves and the simulation time grows as the generations number is increased. This model was presented and used in previous papers to solve patern classification problems [3], having obtained better results than other methods.…”

Section: Obtained Resultsmentioning

confidence: 99%

Comparing Hybrid Systems to Design and Optimize Artificial Neural Networks

Castillo

Arenas

Merelo

et al. 2004

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper we conduct a comparative study between hybrid methods to optimize multilayer perceptrons: a model that optimizes the architecture and initial weights of multilayer perceptrons; a parallel approach to optimize the architecture and initial weights of multilayer perceptrons; a method that searches for the parameters of the training algorithm, and an approach for cooperative co-evolutionary optimization of multilayer perceptrons. Obtained results show that a co-evolutionary model obtains similar or better results than specialized approaches, needing much less training epochs and thus using much less simulation time.

show abstract

“…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%

“…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

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

G-Prop: Global optimization of multilayer perceptrons using GAs

Cited by 134 publications

References 24 publications

A training algorithm for classification of high-dimensional data

A training algorithm for classification of high-dimensional data

Comparing Hybrid Systems to Design and Optimize Artificial Neural Networks

Evolutionary system for prediction and optimization of hardware architecture performance

Contact Info

Product

Resources

About