点击次数：

论文类型：期刊论文

发表时间：2012-12-01

发表刊物：Journal of Theoretical and Applied Information Technology

收录刊物：EI

卷号：46

期号：1

页面范围：114-119

ISSN号：19928645

摘要：In this paper, a smoothing algorithm for training max-min neural networks is proposed. Specifically, we apply a smooth function to approximate max-min functions and use this smoothing technique twice, once to eliminate the inner min operator and once to eliminate the max operator. In place of actual network output by its approximation function, we use all partial derivatives of the approximation function with respect to weight to substitute those of the actual network output. Then, the smoothing algorithm is constructed by the gradient descent method. This algorithm can also be used to solve fuzzy relational equations. Finally, two numerical examples are provided to show the effectiveness of our smoothing algorithm for training max-min neural networks. ? 2005 - 2012 JATIT & LLS. All rights reserved.