Breeding swarms: a new approach to recurrent neural network training

Authors:
Matthew Settles;Paul Nathan;Terence Soule
Affiliations:
University of Idaho, Moscow, ID;University of Idaho, Moscow, ID;University of Idaho, Moscow, ID
Venue:
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Year:
2005

Citing 7
Cited 1

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
Swarm intelligence

Swarm intelligence
Learning with Recurrent Neural Networks

Learning with Recurrent Neural Networks
Noisy Time Series Prediction using Recurrent Neural Networks and Grammatical Inference

Machine Learning
Comparison between Genetic Algorithms and Particle Swarm Optimization

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Evolutionary Optimization Versus Particle Swarm Optimization: Philosophy and Performance Differences

EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Comparison of genetic algorithm and particle swarm optimizer when evolving a recurrent neural network

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI

Research frontier: the evolution of swarm grammars-growing trees, crafting art, and bottom-up design

IEEE Computational Intelligence Magazine

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper shows that a novel hybrid algorithm, Breeding Swarms, performs equal to, or better than, Genetic Algorithms and Particle Swarm Optimizers when training recurrent neural networks. The algorithm was found to be robust and scale well to very large networks, ultimately outperforming Genetic Algorithms and Particle Swarm Optimization in 79 of 80 tested networks. This research shows that the Breeding Swarm algorithm is a viable option when choosing an algorithm to train recurrent neural networks.