Sciweavers

71 search results - page 7 / 15
» Unsupervised Learning of Manifolds via Linear Approximations
Sort
View
90
Voted
CC
2010
Springer
120views System Software» more  CC 2010»
14 years 7 months ago
Lower Bounds for Agnostic Learning via Approximate Rank
We prove that the concept class of disjunctions cannot be pointwise approximated by linear combinations of any small set of arbitrary real-valued functions. That is, suppose that t...
Adam R. Klivans, Alexander A. Sherstov
75
Voted
COLT
1994
Springer
15 years 1 months ago
Lower Bounds on the VC-Dimension of Smoothly Parametrized Function Classes
We examine the relationship between the VCdimension and the number of parameters of a smoothly parametrized function class. We show that the VC-dimension of such a function class ...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...
94
Voted
KDD
2006
ACM
213views Data Mining» more  KDD 2006»
15 years 10 months ago
Learning sparse metrics via linear programming
Calculation of object similarity, for example through a distance function, is a common part of data mining and machine learning algorithms. This calculation is crucial for efficie...
Glenn Fung, Rómer Rosales
ADCM
2006
74views more  ADCM 2006»
14 years 9 months ago
Linearly constrained reconstruction of functions by kernels with applications to machine learning
This paper investigates the approximation of multivariate functions from data via linear combinations of translates of a positive definite kernel from a reproducing kernel Hilbert...
Robert Schaback, J. Werner
72
Voted
SCALESPACE
2007
Springer
15 years 3 months ago
Towards Segmentation Based on a Shape Prior Manifold
Incorporating shape priors in image segmentation has become a key problem in computer vision. Most existing work is limited to a linearized shape space with small deformation modes...
Patrick Etyngier, Renaud Keriven, Jean-Philippe Po...