Abstract
This paper is an extension to the memory retrieval procedure of the B-Matrix approach [6],[17] to neural network learning. The B-Matrix is a part of the interconnection matrix generated from the Hebbian neural network, and in memory retrieval, the B-matrix is clamped with a small fragment of the memory. The fragment gradually enlarges by means of feedback, until the entire vector is obtained. In this paper, we propose the use of delta learning to enhance the retrieval rate of the stored memories.
Abstract (translated by Google)
URL
https://arxiv.org/abs/1103.2741