講演抄録/キーワード |
講演名 |
2008-08-04 15:30
A Hybrid PSO and quasi-Newton Technique for Training of Feedforward Neural Networks ○Hiroshi Ninomiya(Shonan Inst. of Tech.)・Qi-Jun Zhang(Carleton Univ.) CST2008-17 |
抄録 |
(和) |
This paper describes a new technique for training feedforward neural networks. We employ the proposed algorithm for robust neural network training purpose. Conventional neural network training algorithms based on the gradient descent often encounter local minima problems. Recently, some evolutionary algorithms are getting a lot more attention about global search ability but are less-accurate for complicated training task of neural networks. The proposed technique hybridizes local training algorithm based on quasi-Newton method with a recent global optimization algorithm called Particle Swarm Optimization (PSO). The proposed technique provides higher global convergence property than the conventional global optimization technique. Neural network training for some benchmark problems is presented to demonstrate the proposed algorithm. The proposed algorithm achieves more accurate and robust training results than the quasi-Newton method and the conventional PSOs. |
(英) |
This paper describes a new technique for training feedforward neural networks. We employ the proposed algorithm for robust neural network training purpose. Conventional neural network training algorithms based on the gradient descent often encounter local minima problems. Recently, some evolutionary algorithms are getting a lot more attention about global search ability but are less-accurate for complicated training task of neural networks. The proposed technique hybridizes local training algorithm based on quasi-Newton method with a recent global optimization algorithm called Particle Swarm Optimization (PSO). The proposed technique provides higher global convergence property than the conventional global optimization technique. Neural network training for some benchmark problems is presented to demonstrate the proposed algorithm. The proposed algorithm achieves more accurate and robust training results than the quasi-Newton method and the conventional PSOs. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Feedforward neural networks / Particle swarm optimization / quasi-Newton method / Hybrid algorithm / / / / |
文献情報 |
信学技報, vol. 108, 2008年8月. |
資料番号 |
|
発行日 |
2008-07-28 (CST) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
CST2008-17 |