Sciweavers

845 search results - page 19 / 169
» Complexity Dimensions and Learnability
Sort
View
ISBI
2004
IEEE
14 years 9 months ago
Nonlinear Dimension Reduction of fMRI Data: The Laplacian Embedding Approach
In this paper, we introduce the use of nonlinear dimension reduction for the analysis of functional neuroimaging datasets. Using a Laplacian Embedding approach, we show the power ...
Olivier D. Faugeras, Bertrand Thirion
ESA
2008
Springer
137views Algorithms» more  ESA 2008»
13 years 10 months ago
An Almost Space-Optimal Streaming Algorithm for Coresets in Fixed Dimensions
We present a new streaming algorithm for maintaining an -kernel of a point set in Rd using O((1/(d-1)/2 ) log(1/)) space. The space used by our algorithm is optimal up to a small ...
Hamid Zarrabi-Zadeh
IJCNN
2000
IEEE
14 years 24 days ago
VC Dimension Bounds for Product Unit Networks
A product unit is a formal neuron that multiplies its input values instead of summingthem. Furthermore, it has weights acting as exponents instead of being factors. We investigate...
Michael Schmitt
ENTCS
2008
85views more  ENTCS 2008»
13 years 8 months ago
Connectivity Properties of Dimension Level Sets
This paper initiates the study of sets in Euclidean space Rn (n 2) that are defined in terms of the dimensions of their elements. Specifically, given an interval I [0, 1], we ar...
Jack H. Lutz, Klaus Weihrauch
COMPGEOM
2010
ACM
14 years 1 months ago
Lines avoiding balls in three dimensions revisited
Let B be a collection of n arbitrary balls in R3 . We establish an almost-tight upper bound of O(n3+ε ), for any ε > 0, on the complexity of the space F(B) of all the lines t...
Natan Rubin