Sciweavers

5030 search results - page 848 / 1006
» cases 2007
Sort
View
ML
2007
ACM
108views Machine Learning» more  ML 2007»
15 years 6 months ago
Unconditional lower bounds for learning intersections of halfspaces
We prove new lower bounds for learning intersections of halfspaces, one of the most important concept classes in computational learning theory. Our main result is that any statist...
Adam R. Klivans, Alexander A. Sherstov
MST
2007
132views more  MST 2007»
15 years 6 months ago
Odometers on Regular Languages
Odometers or “adding machines” are usually introduced in the context of positional numeration systems built on a strictly increasing sequence of integers. We generalize this no...
Valérie Berthé, Michel Rigo
NA
2007
120views more  NA 2007»
15 years 6 months ago
On choosing "optimal" shape parameters for RBF approximation
Many radial basis function (RBF) methods contain a free shape parameter that plays an important role for the accuracy of the method. In most papers the authors end up choosing this...
Gregory E. Fasshauer, Jack G. Zhang
NA
2007
100views more  NA 2007»
15 years 6 months ago
Periodization strategy may fail in high dimensions
Abstract. We discuss periodization of smooth functions f of d variables for approximation of multivariate integrals. The benefit of periodization is that we may use lattice rules,...
Frances Y. Kuo, Ian H. Sloan, Henryk Wozniakowski
NECO
2007
115views more  NECO 2007»
15 years 6 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...