Sciweavers

NIPS
2004
14 years 24 days ago
Kernel Projection Machine: a New Tool for Pattern Recognition
This paper investigates the effect of Kernel Principal Component Analysis (KPCA) within the classification framework, essentially the regularization properties of this dimensional...
Laurent Zwald, Régis Vert, Gilles Blanchard...
NIPS
2004
14 years 24 days ago
A Direct Formulation for Sparse PCA Using Semidefinite Programming
We examine the problem of approximating, in the Frobenius-norm sense, a positive, semidefinite symmetric matrix by a rank-one matrix, with an upper bound on the cardinality of its...
Alexandre d'Aspremont, Laurent El Ghaoui, Michael ...
NIPS
2004
14 years 24 days ago
Nonparametric Transforms of Graph Kernels for Semi-Supervised Learning
We present an algorithm based on convex optimization for constructing kernels for semi-supervised learning. The kernel matrices are derived from the spectral decomposition of grap...
Xiaojin Zhu, Jaz S. Kandola, Zoubin Ghahramani, Jo...
NIPS
2004
14 years 24 days ago
Semi-supervised Learning on Directed Graphs
Given a directed graph in which some of the nodes are labeled, we investigate the question of how to exploit the link structure of the graph to infer the labels of the remaining u...
Dengyong Zhou, Bernhard Schölkopf, Thomas Hof...
NIPS
2004
14 years 24 days ago
A Probabilistic Model for Online Document Clustering with Application to Novelty Detection
In this paper we propose a probabilistic model for online document clustering. We use non-parametric Dirichlet process prior to model the growing number of clusters, and use a pri...
Jian Zhang 0003, Zoubin Ghahramani, Yiming Yang
NIPS
2004
14 years 24 days ago
Class-size Independent Generalization Analsysis of Some Discriminative Multi-Category Classification
We consider the problem of deriving class-size independent generalization bounds for some regularized discriminative multi-category classification methods. In particular, we obtai...
Tong Zhang
NIPS
2004
14 years 24 days ago
Probabilistic Computation in Spiking Populations
As animals interact with their environments, they must constantly update estimates about their states. Bayesian models combine prior probabilities, a dynamical model and sensory e...
Richard S. Zemel, Quentin J. M. Huys, Rama Nataraj...
NIPS
2004
14 years 24 days ago
Self-Tuning Spectral Clustering
We study a number of open issues in spectral clustering: (i) Selecting the appropriate scale of analysis, (ii) Handling multi-scale data, (iii) Clustering with irregular backgroun...
Lihi Zelnik-Manor, Pietro Perona
NIPS
2004
14 years 24 days ago
The Convergence of Contrastive Divergences
This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We relate the algorithm to the stochastic approximation literature. This enables us t...
Alan L. Yuille