Title
Study Of Neural Network Disturbance Learning And Application In Robocup
Keywords
Machine learning; Neural networks; RoboCup
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.
Publication Date
6-1-2007
Publication Title
High Technology Letters
Volume
13
Issue
2
Number of Pages
203-206
Document Type
Article
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
34347215898 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/34347215898
STARS Citation
Peng, Jun; Wu, Ming; Guo, Rui; and Lin, Kuo Chi, "Study Of Neural Network Disturbance Learning And Application In Robocup" (2007). Scopus Export 2000s. 6551.
https://stars.library.ucf.edu/scopus2000/6551