Particle Swarm Optimization of Neural Network Architectures andWeights

Authors:
Marcio Carvalho;Teresa B. Ludermir
Affiliations:
Federal University of Pernambuco;Federal University of Pernambuco
Venue:
HIS '07 Proceedings of the 7th International Conference on Hybrid Intelligent Systems
Year:
2007

Citing 0
Cited 8

Evolutionary artificial neural networks by multi-dimensional particle swarm optimization

Neural Networks
A notable swarm approach to evolve neural network for classification in data mining

ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Evaluation of global and local training techniques over feed-forward neural network architecture spaces for computer-aided medical diagnosis

Expert Systems with Applications: An International Journal
Learning in the feed-forward random neural network: A critical review

Performance Evaluation
An improved swarm optimized functional link artificial neural network (ISO-FLANN) for classification

Journal of Systems and Software
A hybrid algorithm for artificial neural network training

Engineering Applications of Artificial Intelligence
PSO for reservoir computing optimization

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Evolving multilayer feedforward neural network using adaptive particle swarm algorithm

International Journal of Hybrid Intelligent Systems

Quantified Score

Hi-index	0.01

Visualization

Abstract

The optimization of architecture and weights of feed forward neural networks is a complex task of great importance in problems of supervised learning. In this work we analyze the use of the Particle Swarm Optimization algorithm for the optimization of neural network architectures and weights aiming better generalization performances through the creation of a compromise between low architectural complexity and low training errors. For evaluating these algorithms we apply them to benchmark classification problems of the medical field. The results showed that a PSOPSO based approach represents a valid alternative to optimize weights and architectures of MLP neural networks.