Evolutionary neural networks for nonlinear dynamics modeling

Falco, Ivanoe De; Iazzetta, A.; Natale, Pasquale; Tarantino, Ernesto

doi:10.1007/bfb0056901

Cited by 23 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some authors use binary or real encoding (representation of the networks in a binary or real number string), as proposed by [13,14], or indirect coding, as proposed by [8], but GProp evolves the initial parameters of the network (initial weights and learning constants) using specific genetic operators.…”

Section: Gprop Methodsmentioning

confidence: 99%

Discovering causes of financial distress by combining evolutionary algorithms and artificial neural networks

García

Valdivieso

Merelo

et al. 2008

Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

In this work we compare two soft-computing methods for producing models that are able to predict whether a company is going to have book losses: artificial neural networks (ANNs) and genetic programming (GP). In order to build prediction models that can be applied to an extensive number of practical cases, we need simple models which require a small amount of data. Kohonen's self-organizing map (SOM) is a non-supervised neural network that is usually used as a clustering tool. In our case a SOM has been used to reduce the dimensions of the prediction problem. Traditionally, ANNs have been considered able to produce better classifier structures than GP. In this work we merge the capability of GP for generating classification trees and the feature extraction abilities of SOM, obtaining a classification tool that beats the results yielded using an evolutionary ANN method.

show abstract

Section: Gprop Methodsmentioning

confidence: 99%

Discovering causes of financial distress by combining evolutionary algorithms and artificial neural networks

García

Valdivieso

Merelo

et al. 2008

Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…Some authors use binary or real encoding (representation of the networks in a binary or real number string) [37], [38], or indirect coding [39], [40], but G-Prop evolves the initial parameters of the network (initial weights and learning constants) using specific genetic operators. At the lowest level, an MLP is an object instantiated from the MLP C++ class.…”

Section: The Methodsmentioning

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)

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

“…Normally, networks are trained using gradient descent, but recently evolutionary computation has been used to either evolve the network structure and then learn the weights via gradient descent (e.g. for Multi-Layer perceptrons [25,5,13], and Radial Basis Function Networks (RBF) [21]), or to bypass learning altogether by evolving weight values as well [26]. However, because these methods use feedforward architectures, none of them implement general sequence predictors.…”

Section: Introductionmentioning

confidence: 99%

“…That is, predictors that can detect temporal dependencies in the input data that span an arbitrary number of time steps. The MackeyGlass time-series that is often used to test these methods [21,25,3,5,13], for instance, can be predicted very accurately using a feedforward network with a relatively short time-delay window on the input.…”

Section: Introductionmentioning

confidence: 99%

Modeling systems with internal state using evolino

Wierstra

Gomez

Schmidhuber

2005

Proceedings of the 7th Annual Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework for sequence learning, EVOlution of recurrent systems with LINear Outputs (Evolino), to discover good RNN hidden node weights through evolution, while using linear regression to compute an optimal linear mapping from hidden state to output. Using the Long Short-Term Memory RNN Architecture, Evolino outperforms previous state-of-the-art methods on several tasks: 1) context-sensitive languages, 2) multiple superimposed sine waves.

show abstract

Evolutionary neural networks for nonlinear dynamics modeling

Cited by 23 publications

References 11 publications

Discovering causes of financial distress by combining evolutionary algorithms and artificial neural networks

Discovering causes of financial distress by combining evolutionary algorithms and artificial neural networks

Evolutionary system for prediction and optimization of hardware architecture performance

Modeling systems with internal state using evolino

Contact Info

Product

Resources

About