7 search results - page 1 / 2 » Stochastic Complexity and Generalization Error of a Restrict... |
JMLR
2010
12 years 11 months ago
2010
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...
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
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...
NIPS
2007
13 years 5 months ago
2007
Dynamic Bayesian networks are structured representations of stochastic processes. Despite their structure, exact inference in DBNs is generally intractable. One approach to approx...
FOCI
2007
IEEE
13 years 10 months ago
2007
IEEE
— 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...
IJON
1998
13 years 3 months ago
1998
Bayesian Kullback Ying—Yang dependence reduction system and theory is presented. Via stochastic approximation, implementable algorithms and criteria are given for parameter lear...