Topology optimization and training of recurrent neural networks with Pareto-based multi-objective algorithms: a experimental study

Authors:
M. P. Cuéllar;M. Delgado;M. C. Pegalajar
Affiliations:
Dept. Computer Science and Artificial Intelligence, E.T.S. Ingeniería Informática, University of Granada. Spain;Dept. Computer Science and Artificial Intelligence, E.T.S. Ingeniería Informática, University of Granada. Spain;Dept. Computer Science and Artificial Intelligence, E.T.S. Ingeniería Informática, University of Granada. Spain
Venue:
IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
Year:
2007

Citing 8
Cited 0

Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Recurrent Neural Networks for Prediction: Learning Algorithms,Architectures and Stability

Recurrent Neural Networks for Prediction: Learning Algorithms,Architectures and Stability
An information-theoretic landscape analysis of neuro-controlled embodied organisms

Neural Computing and Applications
Multi-Objective Machine Learning (Studies in Computational Intelligence) (Studies in Computational Intelligence)

Multi-Objective Machine Learning (Studies in Computational Intelligence) (Studies in Computational Intelligence)
A multiobjective genetic algorithm for obtaining the optimal size of a recurrent neural network for grammatical inference

Pattern Recognition
A fast and elitist multiobjective genetic algorithm: NSGA-II

IEEE Transactions on Evolutionary Computation
Multiobjectivity and Complexity in Embodied Cognition

IEEE Transactions on Evolutionary Computation
Constructive learning of recurrent neural networks: limitations of recurrent cascade correlation and a simple solution

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The simultaneous topology optimization and training of neural networks is a problem widely studied in the last years, specially for feedforward models. In the case of recurrent neural networks, the existing proposals attempt to only optimize the number of hidden units, since the problem of topology optimization is more difficult due to the feedback connections in the network structure. In this work, we make a study of the effects and difficulties for the optimization of network connections, hidden neurons and network training for dynamical recurrent models. In the experimental section, the proposal is tested in time series prediction problems.