Implementation of the relaxation process by the interactive activation and competition network

ASIA unversity > 資訊學院 > 資訊傳播學系 > 會議論文 > Item 310904400/6852

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://asiair.asia.edu.tw/ir/handle/310904400/6852

题名:	Implementation of the relaxation process by the interactive activation and competition network
作者:	S. S. Yu;W. H. Tsai
贡献者:	Department of Information Communication
日期:	1991-7
上传时间:	2009-12-23 11:34:42 (UTC+0)
出版者:	Asia University
摘要:	The relaxation process is a useful technique for using contextual information to reduce local ambiguity and achieve global consistency in various applications. It is basically a parallel execution model, adjusting the confidence measures of involved entities based on interrelated hypotheses and confidence measures. On the other hand, the neural network is a computational model with massively parallel execution capability. The output of each neuron depends mainly on the information ovided by other neurons. Therefore, there exist certain common properties in the relaxation process and the neural network technique. A mapping method that makes the interactive activation and etition network perform the relaxation process is proposed. By this method, the neural network technology can be easily adapted tb solve the many problems which have already been solved by the relaxation process. Experimental results of solving a modified version of the n-queens problem on the proposed neural network are given to demonstrate the feasibility of the proposed method.
關聯:	International Joint Conference on Neural Networks, Seatle Washington, U. S. A.,
显示于类别:	[資訊傳播學系] 會議論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	296	检视/开启

在ASIAIR中所有的数据项都受到原著作权保护.