Title :
Training feedforward neural networks using multi-phase particle swarm optimization
Author :
Al-Kazemi, Buthainah ; Mohan, Chilukuri K.
Author_Institution :
Dept. of Electr. & Comput. Eng., Syracuse Univ., NY, USA
Abstract :
The multi-phase particle swarm optimization algorithm (MPPSO) is a variant of the particle swarm optimization algorithm. It simultaneously evolves multiple groups of particles that change their search criterion when changing the phases, and also incorporates hill-climbing. This paper examines the applicability of MPPSO in training feedforward neural network.
Keywords :
evolutionary computation; feedforward neural nets; learning (artificial intelligence); least mean squares methods; optimisation; acyclic networks; evolutionary algorithm; feedforward neural networks training; hill-climbing; input-output mappings; mean squared error; multiphase particle swarm optimization; multiple groups of particles; particle swarm optimization algorithm; search criterion; Backpropagation algorithms; Computer science; Convergence; Evolutionary computation; Feedforward neural networks; Multi-layer neural network; Neural networks; Neurons; Particle swarm optimization; Supervised learning;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1201969
