参数化模糊联想记忆网络的学习算法

基于Dubois提出的带参数ξ的t-模T_ξ，提出了一种参数化的广义模糊联想记忆网络Max-T_ξ FAM。由于T_ξ中参数ξ的作用，在应用中Max-T_ξ FAM有更强的可调性和灵活性。接着利用T_ξ的伴随蕴涵算子，提出了Max-T_ξ FAM的一种有效学习算法。从理论上严格证明了，只要Max-T_ξ FAM能完整可靠地存储所给的多个模式对，则所提出的学习算法一定能找到使得网络能完整可靠存储这些模式对的所有连接权矩阵的最大者。最后，用实验说明了所提出的学习算法的有效性。

Learning algorithm for parameterized fuzzy associative memory

Based on fuzzy composition of maximum operation and a t-norm T_ξ with a parameter ξ proposed by Dubois，a parameterized general fuzzy associate memory Max-T_ξ FAM is presented in this paper.By adjusting parameter ξ，the Max-T_ξ FAM has good adaptability and flexibility in practice.Taking advantage of the concomitant implication operator of T_ξ，a simple effective learning algorithm is proposed for the Max-T_ξ FAM.It is proved theoretically that，for arbitrary given training pattern pairs，if the Max-T_ξ FAM has ability to store them reliably and completely，then the proposed learning algorithm can find the maximum of all connected weight matrices which can ensure that the Max-T_ξ FAM stores reliably these pattern pairs.Finally an experiment is given to illustrate the effectivity of the presented learning algorithm.