Title :
Particle swarms for feedforward neural network training
Author :
Mendes, Rui ; Cortez, Paulo ; Rocha, Miguel ; Neves, José
Author_Institution :
Dept. de Informatica, Univ. do Minho, Braga, Portugal
fDate :
6/24/1905 12:00:00 AM
Abstract :
Particle swarm is an optimization paradigm for real-valued functions, based on the social dynamics of group interaction. We propose its application to the training of neural networks. Comparative tests were carried out, for classification and regression tasks
Keywords :
evolutionary computation; feedforward neural nets; gradient methods; learning (artificial intelligence); optimisation; classification; evolutionary programming; feedforward neural network training; gradient-based algorithms; group interaction; optimization paradigm; particle swarms; real-valued functions; regression; social dynamics; Artificial intelligence; Artificial neural networks; Feedforward neural networks; Genetic programming; Machine learning algorithms; Neural networks; Particle swarm optimization; Problem-solving; Testing; Topology;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007808
