Sciweavers

54 search results - page 5 / 11
» nn 2002
Sort
View
NN
2002
Springer
224views Neural Networks» more  NN 2002»
13 years 10 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
NN
2002
Springer
107views Neural Networks» more  NN 2002»
13 years 10 months ago
Equivariant nonstationary source separation
Most of source separation methods focus on stationary sources, so higher-order statistics is necessary for successful separation, unless sources are temporally correlated. For non...
Seungjin Choi, Andrzej Cichocki, Shun-ichi Amari
NN
2002
Springer
113views Neural Networks» more  NN 2002»
13 years 10 months ago
Control of exploitation-exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Shin Ishii, Wako Yoshida, Junichiro Yoshimoto
ICIP
2002
IEEE
15 years 14 days ago
Hybrid and parallel face classifier based on artificial neural networks and principal component analysis
We present a hybrid and parallel system based on artificial neural networks for a face invariant classifier and general pattern recognition problems. A set of face features is ext...
Peter V. Bazanov, Tae-Kyun Kim, Seok-Cheol Kee, Sa...
COMBINATORICS
2002
84views more  COMBINATORICS 2002»
13 years 10 months ago
Compositions of Random Functions on a Finite Set
If we compose sufficiently many random functions on a finite set, then the composite function will be constant. We determine the number of compositions that are needed, on average...
Avinash Dalal, Eric Schmutz