Sciweavers

2516 search results - page 36 / 504
» When is there a representer theorem
Sort
View
TNN
2008
74views more  TNN 2008»
15 years 6 months ago
Pattern Representation in Feature Extraction and Classifier Design: Matrix Versus Vector
The matrix, as an extended pattern representation to the vector, has proven to be effective in feature extraction. But the subsequent classifier following the matrix-pattern-orien...
Zhe Wang, Songcan Chen, Jun Liu, Daoqiang Zhang
AIML
2004
15 years 7 months ago
Complexity of Strict Implication
abstract. The aim of the present paper is to analyze the complexity of strict implication (together with falsum, conjunction and disjunction). We prove that Ladner's Theorem r...
Félix Bou
FOCM
2010
122views more  FOCM 2010»
15 years 3 months ago
Scattering in Flatland: Efficient Representations via Wave Atoms
This paper presents a numerical compression strategy for the boundary integral equation of acoustic scattering in two dimensions. These equations have oscillatory kernels that we ...
Laurent Demanet, Lexing Ying
ICML
2005
IEEE
16 years 7 months ago
PAC-Bayes risk bounds for sample-compressed Gibbs classifiers
We extend the PAC-Bayes theorem to the sample-compression setting where each classifier is represented by two independent sources of information: a compression set which consists ...
François Laviolette, Mario Marchand
AML
2000
101views more  AML 2000»
15 years 6 months ago
Local order property in nonelementary classes
We study a local version of the order property in several frameworks, with an emphasis on frameworks where the compactness theorem fails: (1) Inside a fixed model, (2) for classes ...
Rami P. Grossberg, Olivier Lessmann