关键词: 模糊联想记忆网络, 训练模式对, T-模, 摄动, 鲁棒性

Abstract: This paper sets up a class of fuzzy associative memories based on the fuzzy composition of max operation（V） and T-Norms，so be called V-T FAM（Fuzzy Associative Memory）.With the fuzzy implication operator of T-Norms，a general learning algorithm is proposed for a class of such V-T FAMs.Since small perturbations of training pattern pairs may cause some disadvantages to performance of a fuzzy neural network，a new concept is established for the robustness of V-T FAMs to perturbations of training pattern pairs.The theoretical researches show that when T-Norms satisfy Lipschitz condition，V-T FAMs have good robustness under the condition of the perturbation factor of β of training pattern pairs by the proposed learning algorithm.Finally，the experiment with which the V-T FAM associated an image with another image is given to testify the theoretical results.

Key words: fuzzy associative memories, training pattern pairs, T-Norms, perturbation, robustness