Sciweavers

8 search results - page 1 / 2
» Comparison of worst case errors in linear and neural network...
Sort
View
TIT
2002
89views more  TIT 2002»
13 years 4 months ago
Comparison of worst case errors in linear and neural network approximation
Sets of multivariable functions are described for which worst case errors in linear approximation are larger than those in approximation by neural networks. A theoretical framework...
Vera Kurková, Marcello Sanguineti
NECO
2007
129views more  NECO 2007»
13 years 4 months ago
Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance
It is well-known that, in unidentifiable models, the Bayes estimation provides much better generalization performance than the maximum likelihood (ML) estimation. However, its ac...
Shinichi Nakajima, Sumio Watanabe
ICTAI
2008
IEEE
13 years 11 months ago
The Performance of Approximating Ordinary Differential Equations by Neural Nets
—The dynamics of many systems are described by ordinary differential equations (ODE). Solving ODEs with standard methods (i.e. numerical integration) needs a high amount of compu...
Josef Fojdl, Rüdiger W. Brause
IJCNN
2000
IEEE
13 years 9 months ago
Recursive Non Linear Models for On Line Traffic Prediction of VBR MPEG Coded Video Sources
Any performance evaluation of broadband networks requires modeling of the actual network traffic. Since multimedia services and especially MPEG coded video streams are expected to...
Anastasios D. Doulamis, Nikolaos D. Doulamis, Stef...
TNN
1998
100views more  TNN 1998»
13 years 4 months ago
A dynamical system perspective of structural learning with forgetting
—Structural learning with forgetting is an established method of using Laplace regularization to generate skeletal artificial neural networks. In this paper we develop a continu...
D. A. Miller, J. M. Zurada