Sciweavers

413 search results - page 60 / 83
» Are Hopfield Networks Faster than Conventional Computers
Sort
View
JMLR
2006
389views more  JMLR 2006»
15 years 5 months ago
A Very Fast Learning Method for Neural Networks Based on Sensitivity Analysis
This paper introduces a learning method for two-layer feedforward neural networks based on sensitivity analysis, which uses a linear training algorithm for each of the two layers....
Enrique Castillo, Bertha Guijarro-Berdiñas,...
PAMI
2011
14 years 8 months ago
Richardson-Lucy Deblurring for Scenes under a Projective Motion Path
— This paper addresses how to model and correct image blur that arises when a camera undergoes ego motion while observing a distant scene. In particular, we discuss how the blurr...
Yu-Wing Tai, Ping Tan, Michael S. Brown
AVSS
2006
IEEE
16 years 21 hour ago
Nonparametric Background Modeling Using the CONDENSATION Algorithm
Background modeling for dynamic scenes is an important problem in the context of real time video surveillance systems. Several nonparametric background models have been proposed t...
Xingzhi Luo, Suchendra M. Bhandarkar, Wei Hua, Hai...
MOBIHOC
2008
ACM
16 years 5 months ago
An O(log n) dominating set protocol for wireless ad-hoc networks under the physical interference model
Dealing with interference is one of the primary challenges to solve in the design of protocols for wireless ad-hoc networks. Most of the work in the literature assumes localized o...
Christian Scheideler, Andréa W. Richa, Paol...
MFCS
2007
Springer
16 years 2 days ago
Communication in Networks with Random Dependent Faults
The aim of this paper is to study communication in networks where nodes fail in a random dependent way. In order to capture fault dependencies, we introduce the neighborhood fault...
Evangelos Kranakis, Michel Paquette, Andrzej Pelc