文章基本信息

标题：Boltzmann Machines with Bounded Continuous Random Variables
本地全文：下载
作者：Muneki YASUDA ; Kazuyuki TANAKA
期刊名称：Interdisciplinary Information Sciences
印刷版ISSN：1340-9050
电子版ISSN：1347-6157
出版年度：2007
卷号：13
期号：1
页码：25-31
DOI：10.4036/iis.2007.25
出版社：The Editorial Committee of the Interdisciplinary Information Sciences
摘要：We propose a Boltzmann machine formulated as a probabilistic model where every random variable takes bounded continuous values, and we derive the Thouless–Anderson–Palmer equation for the model. The proposed model includes the non-negative Boltzmann machine and the Sherrington–Kirkpatrick model with spin- S at S →∞ as a special case. It is known that the Sherrington–Kirkpatrick model with spin- S has a spin glass phase. Thus, the proposed Boltzmann machine is expected to be able to learn practical complex data.
关键词：machine learning;non-negative boltzmann machine;Plefka expansion;TAP equation;SK model