Boltzmann Machines with Bounded Continuous Random Variables

Muneki YASUDA, Kazuyuki TANAKA
2007 Interdisciplinary Information Sciences  
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 ! 1 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
more » ... le to learn practical complex data.
doi:10.4036/iis.2007.25 fatcat:qjp5guj55zfh3n2oo7kilj6hqy