Sciweavers

4894 search results - page 711 / 979
» The Guarding Problem - Complexity and Approximation
Sort
View
IJCV
1998
103views more  IJCV 1998»
13 years 8 months ago
Dense Non-Rigid Motion Estimation in Sequences of Medical Images Using Differential Constraints
We describe a new method for computing the displacement vector field in time sequences of 2D or 3D images (4D data). The method is energy-minimizing on the space of correspondence...
Serge Benayoun, Nicholas Ayache
ML
2002
ACM
168views Machine Learning» more  ML 2002»
13 years 8 months ago
On Average Versus Discounted Reward Temporal-Difference Learning
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
John N. Tsitsiklis, Benjamin Van Roy
ML
2002
ACM
146views Machine Learning» more  ML 2002»
13 years 8 months ago
Kernel Matching Pursuit
Matching Pursuit algorithms learn a function that is a weighted sum of basis functions, by sequentially appending functions to an initially empty basis, to approximate a target fu...
Pascal Vincent, Yoshua Bengio
KBS
1998
66views more  KBS 1998»
13 years 8 months ago
A hierarchical case representation using context guided retrieval
This paper presents a hierarchical case representation using a context guided retrieval method. The performance of this method is compared to that of a simpler flat file represe...
Ian D. Watson, Srinath Perera
NN
2002
Springer
224views Neural Networks» more  NN 2002»
13 years 8 months ago
Optimal design of regularization term and regularization parameter by subspace information criterion
The problem of designing the regularization term and regularization parameter for linear regression models is discussed. Previously, we derived an approximation to the generalizat...
Masashi Sugiyama, Hidemitsu Ogawa