1406 search results - page 45 / 282 » Learning Pseudo-independent Models: Analytical and Experimen... |
101
click to vote
NIPS
2000
15 years 1 months ago
2000
Bayesian networks are graphical representations of probability distributions. In virtually all of the work on learning these networks, the assumption is that we are presented with...
84
Voted
CORR
2010
Springer
15 years 18 days ago
2010
Springer
We present an approach to semi-supervised learning based on an exponential family characterization. Our approach generalizes previous work on coupled priors for hybrid generative/...
79
Voted
ECAI
2004
Springer
15 years 5 months ago
2004
Springer
In this paper we propose a novel classification algorithm that fits models of different complexity on separate regions of the input space. The goal is to achieve a balance betwee...
80
Voted
ICML
2007
IEEE
16 years 1 months ago
2007
IEEE
We introduce quadratically gated mixture of experts (QGME), a statistical model for multi-class nonlinear classification. The QGME is formulated in the setting of incomplete data,...
94
Voted
ICML
2003
IEEE
16 years 1 months ago
2003
IEEE
We show a close relationship between the Expectation - Maximization (EM) algorithm and direct optimization algorithms such as gradientbased methods for parameter learning. We iden...