Two-Phase Pattern Search-based Learning Method for Multi-layer Neural Network
スポンサーリンク
概要
- 論文の詳細を見る
A new multi-layer artificial neural network learning algorithm based on pattern search method is proposed. The learning model has two phases-a pattern search phase, and a local minimum-escaping phase. In the pattern search phase, our method performs local search iteratively and minimize the error measure function along with the set of descent directions of the error measure directly and finds the nearest minima efficiently. When the network gets stuck in local minima, the local minimum-escaping phase attempts to fill up the valley by modifying temperature parameters in ascent direction of the error measure. Thus, the two phases are repeated until the network gets out of local minima. The learning model is designed to provide a very simple and effective means of searching the minima of objective function directly without any knowledge of its derivatives. We test this algorithm on benchmark problems, such as exclusive-or (XOR), parity, Arabic numerals recognition, function approximation problems and a real world classification task. For all problems, the systems are shown be trained efficiently by our method. As a simple direct search method, it can be applied in hardware implementations easily.
- 社団法人 電気学会の論文
- 2004-03-01
著者
-
TAMURA Hiroki
Faculty of Engineering, Toyama University
-
ISHII Masahiro
Faculty of Engineering, Toyama University
-
Tamura Hiroki
Faculty Of Engineering Toyama University
-
Tang Zheng
Faculty Of Engineering Miyazaki University
-
Ishii Masahiro
Faculty Of Engineering Toyama University
-
Ishii Masahiro
Faculty Of Business Administration Daito Bunka University
-
Wang Xugang
Faculty Of Engineering Toyama University
-
ZHENG Tang
Faculty of Engineering, Toyama University
-
Zheng Tang
Faculty Of Engineering Toyama University
関連論文
- Multilayer Network Learning Algorithm Based on Pattern Search Method(Neural Networks and Bioengineering)
- A Local Search Based Learning Method for Multiple-Valued Logic Networks(Neural Networks and Bioengineering)
- A Method of Learning for Multi-Layer Networks
- A Fast and Reliable Approach to TSP using Positively Self-feedbacked Hopfield Networks
- Objective Function Adjustment Algorithm for Combinatorial Optimization Problems(Numerical Analysis and Optimization)
- An Improved Artificial Immune Network Model(Neural Networks and Bioengineering)
- A Neural-based Algorithm for Topological Via-minimization Problem
- A New Method to Solve the Constraint Satisfaction Problem Using the Hopfield Neural Network
- An Artificial Immune Network with Multi-layered B Cells Architecture
- An Artificial Immune System Architecture and Its Applications(Neural Networks and Bioengineering)