PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Semi-supervised learning with Gaussian fields
Jakob Verbeek and Nikos Vlassis
(2005) Technical Report. University of Amsterdam.


Gaussian fields (GF) have recently received considerable attention for dimension reduction and semi-supervised classification. This paper presents two contribu- tions. First, we show how the GF framework can be used for regression tasks on high-dimensional data. We consider an active learning strategy based on entropy minimization and a maximum likelihood model selection method. Second, we show how a recent generalization of the Locally Linear Embedding algorithm for correspondence learning can also be cast into the GF framework, which obviates the need to choose a representation dimensionality.

EPrint Type:Monograph (Technical Report)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:4224
Deposited By:Jakob Verbeek
Deposited On:05 December 2008