Chen Hsin, Fleury Patrice C D, Murray Alan F
Department of Electrical Engineering, National Tsing-Hua University, Hsin-Chu 30055, Taiwan.
IEEE Trans Neural Netw. 2006 May;17(3):755-70. doi: 10.1109/TNN.2006.873278.
This paper presents the VLSI implementation of the continuous restricted Boltzmann machine (CRBM), a probabilistic generative model that is able to model continuous-valued data with a simple and hardware-amenable training algorithm. The full CRBM system consists of stochastic neurons whose continuous-valued probabilistic behavior is mediated by injected noise. Integrating on-chip training circuits, the full CRBM system provides a platform for exploring computation with continuous-valued probabilistic behavior in VLSI. The VLSI CRBM's ability both to model and to regenerate continuous-valued data distributions is examined and limitations on its performance are highlighted and discussed.
本文介绍了连续受限玻尔兹曼机（CRBM）的超大规模集成电路（VLSI）实现，CRBM是一种概率生成模型，能够通过简单且适合硬件的训练算法对连续值数据进行建模。完整的CRBM系统由随机神经元组成，其连续值概率行为由注入噪声介导。集成了片上训练电路后，完整的CRBM系统为在VLSI中探索具有连续值概率行为的计算提供了一个平台。研究了VLSI CRBM对连续值数据分布进行建模和再生的能力，并突出和讨论了其性能上的局限性。
