基于Lukasiewicz t-模的模糊双向联想记忆网络的有效学习算法

利用t-模的伴随蕴涵算子，为基于Max和TL合成的模糊双向联想记忆网络Max-TLFBAM提供了一种新的学习算法，此处TL是Lukasiewicz t-模算子。从理论上严格证明了，只要存在有连接权矩阵对使得任意给定的模式对集成为Max-TLFBAM的平衡态集，则依该学习算法所确定的连接权矩阵对是所有这样的连接权矩阵对中的最大者。并用实验验证该学习算法的有效性。

Efficient learning algorithm for Fuzzy bi-directional associative memory based on Lukasiewicz's t-Norm

Taking advantage of the concomitant implication operator of T_ L , which is a t-norm, a simple efficient learning algorithm was proposed for the fuzzy bi-directional associative memory based on fuzzy composition of Max and T_ L (Max-T_ L FBAM). It is proved theoretically that, if there is a connected weight matrix which make arbitrarily given pattern pairs set become stability state set of Max-T_ L FBAM, then the proposed learning algorithm can find the maximum of all connected weight matrices . An experiment was given to test the effectiveness of the presented learning algorithm.