In this paper, we consider the asymptotic form of the generalization error for the restricted Boltzmann machine in Bayesian estimation. It has been shown that obtaining the maximu...
In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standa...
Dynamic Bayesian networks are structured representations of stochastic processes. Despite their structure, exact inference in DBNs is generally intractable. One approach to approx...
— A learning machine is called singular if its Fisher information matrix is singular. Almost all learning machines used in information processing are singular, for example, layer...
Bayesian Kullback Ying—Yang dependence reduction system and theory is presented. Via stochastic approximation, implementable algorithms and criteria are given for parameter lear...