Restricted Boltzmann machine associative memory

Abstract

Restricted Boltzmann machine associative memory (RBMAM) is proposed in this paper. RBMAM memorizes patterns using contrastive divergence learning procedure. It recalls by calculating the reconstruction of pattern using conditional probability. In order to examine the performance of the proposed RBMAM, extensive computer simulations have been carried out. As the result, it has shown that the performance of RBMAM is overwhelming compared with the conventional neural network associative memories. For example as for storage capacity, RBMAM can store about from 2N hidden to 4N hideen patterns, where N hidden denotes the number of neurons in the hidden layer. Similarly we have obtained superior performance of RBMAM in respect of noise tolerance and pattern complement.

Graph Signal Recovery Using Restricted Boltzmann Machines

“…Content addressable memory. An RBM can be considered as a content addressable memory [17]. By a content-addressable memory system, we mean that an RBM is designed to store a number of patterns so that they can be retrieved from noisy or partial cues.…”