Sciweavers

766 search results - page 92 / 154
» Variations on U-Shaped Learning
Sort
View
106
Voted
NIPS
1996
15 years 2 months ago
Radial Basis Function Networks and Complexity Regularization in Function Learning
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function netwo...
Adam Krzyzak, Tamás Linder
102
Voted
CORR
2008
Springer
147views Education» more  CORR 2008»
15 years 24 days ago
A Minimum Relative Entropy Principle for Learning and Acting
This paper proposes a method to construct an adaptive agent that is universal with respect to a given class of experts, where each expert is designed specifically for a particular...
Pedro A. Ortega, Daniel A. Braun
96
Voted
JFR
2006
75views more  JFR 2006»
15 years 20 days ago
Topological map learning from outdoor image sequences
We propose an approach to building topological maps of environments based on image sequences. The central idea is to use manifold constraints to find representative feature protot...
Xuming He, Richard S. Zemel, Volodymyr Mnih
105
Voted
ICCV
2009
IEEE
1419views Computer Vision» more  ICCV 2009»
16 years 5 months ago
On Feature Combination for Multiclass Object Classification
A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. Whil...
Peter Gehler, Sebastian Nowozin
111
Voted
ICCV
2007
IEEE
16 years 2 months ago
An Invariant Large Margin Nearest Neighbour Classifier
The k-nearest neighbour (kNN) rule is a simple and effective method for multi-way classification that is much used in Computer Vision. However, its performance depends heavily on ...
M. Pawan Kumar, Philip H. S. Torr, Andrew Zisserma...