inria-00321133, version 1
Gaussian fields for semi-supervised regression and correspondence learning
Jakob Verbeek
1, 2Nikos Vlassis a, 2
Pattern Recognition 39 (2006) 1864 – 1875
Abstract: Gaussian fields (GF) have recently received considerable attention for dimension reduction and semi-supervised classification. In this paper we show how the GF framework can be used for semi-supervised regression on high-dimensional data. We propose an active learning strategy based on entropy minimization and a maximum likelihood model selection method. Furthermore, we show how a recent generalization of the LLE algorithm for correspondence learning can be cast into the GF framework, which obviates the need to choose a representation dimensionality.
- a – Technical University of Crete
- 1: LEAR (IMAG-INRIA Rhône-Alpes / GRAVIR)
- CNRS : FR71 – CNRS : UMR5527 – INRIA – Université Joseph Fourier - Grenoble I – Institut National Polytechnique de Grenoble (INPG)
- 2: Intelligent Systems Lab. (ISLA)
- University of Amsterdam
- Domain : Computer Science/Learning
- Keywords : Gaussian fields – Regression – Active learning – Model selection
- inria-00321133, version 1
- http://hal.inria.fr/inria-00321133
- oai:hal.inria.fr:inria-00321133
- From: Jakob Verbeek
- Submitted on: Wednesday, 16 February 2011 16:32:45
- Updated on: Friday, 18 February 2011 14:08:34
Associated documents
Export