251 search results - page 8 / 51 » Approximation and Estimation Bounds for Artificial Neural Ne... |
UAI
2003
13 years 8 months ago
2003
In this paper, we introduce a method for approximating the solution to inference and optimization tasks in uncertain and deterministic reasoning. Such tasks are in general intract...
CDC
2008
IEEE
14 years 2 months ago
2008
IEEE
— This paper proposes a novel discretetime veloc ity observer which uses neural network and sliding mode for unknown continuous time mechanical systems. The neural observer i...
NIPS
2001
13 years 9 months ago
2001
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...
NN
2002
Springer
2002
Springer
Optimal design of regularization term and regularization parameter by subspace information criterion
13 years 7 months ago
The problem of designing the regularization term and regularization parameter for linear regression models is discussed. Previously, we derived an approximation to the generalizat...
ICANN
2009
Springer
14 years 2 months ago
2009
Springer
Backpropagation of errors is not only hard to justify from biological perspective but also it fails to solve problems requiring complex logic. A simpler algorithm based on generati...