• Corpus ID: 236087516

Otimizacao de Redes Neurais atraves de Algoritmos Geneticos Celulares

  title={Otimizacao de Redes Neurais atraves de Algoritmos Geneticos Celulares},
  author={Anderson Aparecido da Silva and Teresa Bernarda Ludermir},
Abstract – This works proposes a methodology to searching for automatically Artificial Neural Networks (ANN) by using Cellular Genetic Algorithm (CGA). The goal of this methodology is to find compact networks whit good performance for classification problems. The main reason for developing this work is centered at the difficulties of configuring compact ANNs with good performance rating. The use of CGAs aims at seeking the components of the RNA in the same way that a common Genetic Algorithm… 


Evolving Artificial Neural Networks
Learning and evolution are two fundamental forms of adaptation. There has been a great interest in combining learning and evolution with artificial neural networks (ANN’s) in recent years. This
An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems
  • E. Cantú-Paz, C. Kamath
  • Computer Science, Medicine
    IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2005
An empirical evaluation of eight combinations of EAs and NNs on 15 public-domain and artificial data sets is presented to identify the methods that consistently produce accurate classifiers that generalize well.
Clustering and co-evolution to construct neural network ensembles: An experimental study
This approach creates neural network ensembles in an innovative way, by explicitly partitioning the input space through a clustering method, which considerably reduces the execution time without prejudicing the accuracy, even when a distributed implementation is not used.
A Cellular Genetic Algorithm for Multiobjective Optimization
This paper introduces a new cellular genetic algorithm for solving multiobjective continuous optimization problems. Our approach is characterized by using an external archive to store non-dominated
Genetic algorithm for reservoir computing optimization
This paper presents reservoir computing optimization using Genetic Algorithm, a method to optimize the choice of global parameters using genetic algorithm that was applied on a real problem of time series forecasting.
Cellular Genetic Algorithms
This chapter introduces the applications of cellular automata in genetic algorithms, which makes it especially suitable for dealing with complex and nonlinear problems which are difficult to be solved by general searching methods.
Optimization of the weights and asymmetric activation function family of neural network for time series forecasting
The main idea is to optimize, simultaneously, the weights and activation function used in a Multilayer Perceptron (MLP), through an approach that combines the advantages of simulated annealing, tabu search and a local learning algorithm.
PROBEN 1 - a set of benchmarks and benchmarking rules for neural network training algorithms
The purpose of the problem and rule collection is to give researchers easy access to data for the evaluation of their algorithms and networks and to make direct comparison of the published results feasible.
Particle Swarm Optimization of Feed-Forward Neural Networks with Weight Decay
This work analyzes the use of the Particle Swarm Optimization algorithm and the cooperative variant with the weight decay mechanism for neural network training aiming better generalization performances and applies them to benchmark classification problems of the medical field.
A Modal Symbolic Classifier for selecting time series models
A supervised classification method originating from the symbolic data analysis field is proposed for the model selection problem, and has obtained the lowest classification errors among all the tested algorithms.