Sciweavers

161 search results - page 8 / 33
» Stable Computations with Gaussian Radial Basis Functions
Sort
View
AAAI
2011
12 years 8 months ago
Value Function Approximation in Reinforcement Learning Using the Fourier Basis
We describe the Fourier Basis, a linear value function approximation scheme based on the Fourier Series. We empirically evaluate its properties, and demonstrate that it performs w...
George Konidaris, Sarah Osentoski, Philip Thomas
ICTAI
2002
IEEE
14 years 1 months ago
Function Approximation Using Robust Wavelet Neural Networks
Wavelet neural networks (WNN) have recently attracted great interest, because of their advantages over radial basis function networks (RBFN) as they are universal approximators bu...
Sheng-Tun Li, Shu-Ching Chen
ICASSP
2011
IEEE
13 years 5 days ago
Arccosine kernels: Acoustic modeling with infinite neural networks
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
Chih-Chieh Cheng, Brian Kingsbury
COMPUTING
2006
112views more  COMPUTING 2006»
13 years 8 months ago
Fast Summation of Radial Functions on the Sphere
Radial functions are a powerful tool in many areas of multidimensional approximation, especially when dealing with scattered data. We present a fast approximate algorithm for the ...
Jens Keiner, Stefan Kunis, Daniel Potts
CVPR
2008
IEEE
14 years 10 months ago
Fast and robust numerical solutions to minimal problems for cameras with radial distortion
A number of minimal problems of structure from motion for cameras with radial distortion have recently been studied and solved in some cases. These problems are known to be numeri...
Karl Åström, Klas Josephson, Martin Byr...