A Pipeline Structure for the Sequential Boltzmann Machine

Hongbing ZHU  Mamoru SASAKI  Takahiro INOUE  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E82-A   No.6   pp.920-926
Publication Date: 1999/06/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section of Papers Selected from 1998 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC '98))
Category: 
Keyword: 
sequential Boltzmann machine,  neural network,  pipeline structure,  parallel-transit-evaluation algorithm,  

Full Text: PDF>>
Buy this Article




Summary: 
In this paper, by making good use of the parallel-transit-evaluation algorithm and sparsity of the connection between neurons, a pipeline structure is successfully introduced to the sequential Boltzmann machine processor. The novel structure speeds up nine times faster than the previous one, with only the 12% rise in hardware resources under 10,000 neurons. The performance is confirmed by designing it using 1.2 µm CMOS process standard cells and analyzing the probability of state-change.