Title :
Artificial neural networks design based on modified adaptive particle swarm optimization
Author :
Cheng, Jui-Chuan ; Su, Te-Jen ; Huang, Ming-Yuan ; Juang, Chi-Yuan
Author_Institution :
Dept. of Electron. Eng., Nat. Kaohsiung Univ. of Appl. Sci., Kaohsiung, Taiwan
Abstract :
This paper presents a weights training method of the artificial neural networks (ANN), which combines modified adaptive particle swarm optimization (MAPSO) with Back-propagation (BP) to apply to function approximation. BP is an approximate steepest descent algorithm, hence some inherent problems are frequently encountered in the use of this algorithm, e.g., very slow convergence speed in training, easily to get stuck in a local minimum, etc. This study uses the particle swarm optimization (PSO) method to avoid this problem. From the demonstrated examples, compared with PSO-ANN, APSO-ANN, we have obtained the better performance, better approximation and less convergence generations from the proposed MAPSO-ANN.
Keywords :
backpropagation; function approximation; gradient methods; mathematics computing; neural nets; particle swarm optimisation; approximate steepest descent algorithm; artificial neural networks design; back-propagation; function approximation; modified adaptive particle swarm optimization; weights training method; Approximation algorithms; Artificial neural networks; Convergence; Function approximation; Neurons; Particle swarm optimization; Training;
Conference_Titel :
Next Generation Information Technology (ICNIT), 2011 The 2nd International Conference on
Conference_Location :
Gyeongju
Print_ISBN :
978-1-4577-0266-2
Electronic_ISBN :
978-89-88678-39-8