Department of Electrical Engineering, Utah State University, Logan, UT 84322; Department of Electrical and Computer Engineering, Syracuse University, Syracuse, NY 13210.
IEEE Trans Pattern Anal Mach Intell. 1985 Mar;7(3):358-60. doi: 10.1109/tpami.1985.4767667.
Monte Carlo simulations of the continuous Moore-Penrose generalized inverse associative memory (Kohonen [l]) have shown that the noise-to-signal ratio is improved on recall in the autoassociative case as long as the number of vector pairs stored is less than the number of components per vector. In the heteroassociative case, however, the noise-to-signal ratio may actually be greatly increased upon recall, particularly as the number of vector pairs stored approaches the number of components per vector. The increase in output noise-to-signal ratio in the heteroassociative case is found to be due to the fact that the inverse of the product of the key vector matrix with its transpose may increase without bound in spite of the fact that the key vectors are linearly independent.
蒙特卡罗模拟的连续 Moore-Penrose 广义逆联想记忆（Kohonen [1]）表明，只要存储的向量对数量小于每个向量的分量数量，在自联想情况下，回忆时的信噪比就会提高。然而，在异联想情况下，回忆时信噪比实际上可能会大大增加，特别是当存储的向量对数量接近每个向量的分量数量时。在异联想情况下，输出噪声与信号的比率增加的原因是，尽管关键向量是线性无关的，但关键向量矩阵与其转置的乘积的逆可能会无限增加。
