Multiobjective Hybrid Optimization and Training of Recurrent Neural Networks

ArticleinIEEE TRANSACTIONS ON CYBERNETICS 38(2):381-403 · May 2008with27 Reads
Impact Factor: 6.22 · DOI: 10.1109/TSMCB.2007.912937 · Source: PubMed

    Abstract

    The application of neural networks to solve a problem involves tasks with a high computational cost until a suitable network is found, and these tasks mainly involve the selection of the network topology and the training step. We usually select the network structure by means of a trial-and-error procedure, and we then train the network. In the case of recurrent neural networks (RNNs), the lack of suitable training algorithms sometimes hampers these procedures due to vanishing gradient problems. This paper addresses the simultaneous training and topology optimization of RNNs using multiobjective hybrid procedures. The proposal is based on the SPEA2 and NSGA2 algorithms for making hybrid methods using the Baldwinian hybridization strategy. We also study the effects of the selection of the objectives, crossover, and mutation in the diversity during evolution. The proposals are tested in the experimental section to train and optimize the networks in the competition on artificial time-series (CATS) benchmark.