MOBIHOC
2010
ACM
13 years 10 months ago
2010
ACM
In geographic (or geometric) routing, messages are expected to route in a greedy manner: the current node always forwards a message to its neighbor node that is closest to the des...
IJCV
2010
13 years 11 months ago
2010
Abstract Image alignment has been a long standing problem in computer vision. Parameterized Appearance Models (PAMs) such as the Lucas-Kanade method, Eigentracking, and Active Appe...
TIP
2002
14 years 2 days ago
2002
In this paper, we examine the problem of locating an object in an image when size and rotation are unknown. Previous work has shown that with known geometric parameters, an image r...
TNN
1998
14 years 2 days ago
1998
—In this letter we point out that multilayer neural networks (MLP’s) with either sigmoidal units or radial basis functions can be given a canonical form with positive interunit...
NN
2000
Springer
14 years 6 days ago
2000
Springer
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
JCO
2007
14 years 10 days ago
2007
The Multidimensional Assignment Problem (MAP) is an NP-hard combinatorial optimization problem occurring in many applications, such as data association, target tracking, and resou...
MOR
2006
14 years 11 days ago
2006
We apply the method known as simulated annealing to the following problem in convex optimization: minimize a linear function over an arbitrary convex set, where the convex set is ...
CORR
2007
Springer
14 years 12 days ago
2007
Springer
Results of neural network learning are always subject to some variability, due to the sensitivity to initial conditions, to convergence to local minima, and, sometimes more dramat...
ISCI
2008
14 years 13 days ago
2008
A biclustering algorithm, based on a greedy technique and enriched with a local search strategy to escape poor local minima, is proposed. The algorithm starts with an initial rand...
CPHYSICS
2006
14 years 14 days ago
2006
A new stochastic clustering algorithm is introduced that aims to locate all the local minima of a multidimensional continuous and differentiable function inside a bounded domain. ...