Sciweavers

361 search results - page 26 / 73
» Minimization of Error Functionals over Perceptron Networks
Sort
View
JCB
2002
70views more  JCB 2002»
14 years 9 months ago
Strong Feature Sets from Small Samples
For small samples, classi er design algorithms typically suffer from over tting. Given a set of features, a classi er must be designed and its error estimated. For small samples, ...
Seungchan Kim, Edward R. Dougherty, Junior Barrera...
ICANN
2010
Springer
14 years 9 months ago
Deep Bottleneck Classifiers in Supervised Dimension Reduction
Deep autoencoder networks have successfully been applied in unsupervised dimension reduction. The autoencoder has a "bottleneck" middle layer of only a few hidden units, ...
Elina Parviainen
ICMCS
2006
IEEE
154views Multimedia» more  ICMCS 2006»
15 years 3 months ago
Implementation and Evolution of Packet Striping for Media Streaming Over Multiple Burst-Loss Channels
Modern mobile devices are multi-homed with WLAN and WWAN communication interfaces. In a community of nodes with such multihomed devices — locally inter-connected via high-speed ...
Gene Cheung, Puneet Sharma, Sung-Ju Lee
DCOSS
2008
Springer
14 years 11 months ago
An Information Theoretic Framework for Field Monitoring Using Autonomously Mobile Sensors
We consider a mobile sensor network monitoring a spatio-temporal field. Given limited caches at the sensor nodes, the goal is to develop a distributed cache management algorithm to...
Hany Morcos, George Atia, Azer Bestavros, Ibrahim ...
EDBT
2008
ACM
150views Database» more  EDBT 2008»
15 years 9 months ago
Finding time-dependent shortest paths over large graphs
The spatial and temporal databases have been studied widely and intensively over years. In this paper, we study how to answer queries of finding the best departure time that minim...
Bolin Ding, Jeffrey Xu Yu, Lu Qin