Title :
Restricted Boltzmann machine associative memory
Author :
Nagatani, Keiji ; Hagiwara, Manabu
Author_Institution :
Grad. Sch. of Sci. & Technol, Keio Univ., Yokohama, Japan
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 2Nhidden to ANhideen patterns, where Nhidden 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.
Keywords :
Boltzmann machines; content-addressable storage; learning (artificial intelligence); RBMAM; conditional probability; contrastive divergence learning procedure; neural network associative memories; noise tolerance; pattern complement; pattern reconstruction calculation; restricted Boltzmann machine associative memory; storage capacity; Associative memory; Biological neural networks; Bit error rate; Hidden Markov models; Noise; Training; Vectors;
Conference_Titel :
Neural Networks (IJCNN), 2014 International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-6627-1
DOI :
10.1109/IJCNN.2014.6889573