محاسبه ظرفیت شبکه عصبی هاپفیلد و ارائه روش عملی افزایش حجم حافظه

Abstract

The capacity of the Hopfield model has been considered as an imortant parameter in using this model. In this paper, the Hopfield neural network is modeled as a Shannon Channel and an upperbound to its capacity is found. For achieving maximum memory, we focus on the training algorithm of the network, and prove that the capacity of the network is bounded by the maximum number of the orthogonal training patterns. Then, the pratical memory of the network, for noiseless and noisy inputs, by appropiate coding of the training patterns is examined. Finally, the theoretical results and the increase rate of the memory is evaluated by simulation