| Study of neural network disturbance learning and application in RoboCup |
| |
| 作者姓名： | 彭军 Wu Ming Guo Rui Kuo-chi Lin |
| |
| 作者单位： | [1]School of Information Science and Engineering, Central South University, Changsha 410075, P.R.China [2]Institute for Simulation and Training, University of Central Florida, Orlando, FL32826, U.S.A. |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) |
| |
| 摘 要： | To solve the problem of convergence to a local optimum in the multi-layer feedforward neural network, a new disturbance gradient algorithm is proposed. Through introducing random disturbance into the training process, the algorithm can avoid being trapped into the local optimum. The random disturbance obeys the Boltzmann distribution. The convergence of the algorithm to the global optimum is statistically guaranteed. The application of the algorithm in RoboCup, which is a complex multi-agent system, is discussed. Experiment results illustrate the learning efficiency and generalization ability of the proposed algorithm.
|
| 关 键 词： | 神经网络 干扰学习 机械记忆 计算机 |
Study of neural network disturbance learning and application in RoboCup |
| |
| Peng Jun,Wu Ming,Guo Rui,Kuo-chi Lin.Study of neural network disturbance learning and application in RoboCup[J].High Technology Letters,2007,13(2):203-206. |
| |
| Authors: | Peng Jun Wu Ming Guo Rui Kuo-chi Lin |
| |
| Abstract: | To solve the problem of convergence to a local optimum in the multi-layer feedforward neural network , a new disturbance gradient algorithm is proposed. Through introducing random disturbance into the training process, the algorithm can avoid being trapped into the local optimum. The random disturbance obeys the Boltzmann distribution. The convergence of the algorithm to the global optimum is statistically guaranteed. The application of the algorithm in RoboCup, which is a complex multi-agent system, is discussed . Experiment results illustrate the learning efficiency and generalization ability of the proposed algorithm. |
| |
| Keywords: | machine learning neural networks RoboCup |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
