Learning Coefficient in Bayesian Estimation of Restricted Boltzmann Machine AS2012 Special Volume, part 2: This issue includes a second series of papers from talks, posters and collaborations resulting from and inspired by the Algebraic Statistics in the Alleghenies Conference at Penn State, which took place in July 2012. Learning coefficient resolution of singularities generalization error training error We consider the real log canonical threshold for the learning model in Bayesian estimation. This threshold corresponds to a learning coefficient of generalization error in Bayesian estimation, which serves to measure learning efficiency in hierarchical learning models [30, 31, 33]. In this paper, we clarify the ideal which gives the log canonical threshold of the restricted Boltzmann machine and consider the learning coefficients of this model. Aoyagi, Miki 2013 2013 Article application/pdf islandora:1007822 http://hdl.handle.net/10560/islandora:1007822 MATH / Applied Mathematics Illinois Institute of Technology Journal of Algebraic Statistics en Open Access