A pipeline structure for the sequential Boltzmann machine

作     者：Zhu, HB Sasaki, M Inoue, T 

作者机构：Kumamoto Univ Informat Proc Ctr Kumamoto 8608555 Japan Kumamoto Univ Fac Engn Dept Elect & Comp Engn Kumamoto 8608555 Japan 

出 版 物：《IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES》 (电子信息通信学会汇刊：电子学、通信及计算机科学基础)

年 卷 期：1999年第E82A卷第6期

页      面：920-926页

核心收录：

学科分类：0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：sequential Boltzmann machine neural network pipeline structure parallel-transit-evaluation algorithm 

摘      要：In this paper, by making good use of the parallel-transit-evaluation algorithm [11] 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 Easter than the previous one[ll], with only the 12% rise in hardware resources under 10,000 neurons. The performance is confirmed by designing it using 1.2 mu m CMOS process standard cells and analyzing the probability of state-change.