Sciweavers

499 search results - page 8 / 100
» Why neighbor-joining works
Sort
View
JMLR
2010
106views more  JMLR 2010»
13 years 4 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
JOT
2008
88views more  JOT 2008»
13 years 9 months ago
It depends on what you mean by 'working'
Often efforts to change techniques or processes are met by "But its working, why change now?" Usually the impetous for change comes from someone who does not believe it ...
John McGregor
CHI
2000
ACM
14 years 2 months ago
A diary study of information capture in working life
Despite the increasing number of new devices entering the market allowing the capture or recording of information (whether it be marks on paper, scene, sound or moving images), th...
Barry A. T. Brown, Abigail Sellen, Kenton O'Hara
CORR
2004
Springer
106views Education» more  CORR 2004»
13 years 9 months ago
Why Delannoy numbers?
This article is not a research paper, but a little note on the history of combinatorics: we present here a tentative short biography of Henri Delannoy, and a survey of his most no...
Cyril Banderier, Sylviane R. Schwer
BMCBI
2007
148views more  BMCBI 2007»
13 years 10 months ago
BPhyOG: An interactive server for genome-wide inference of bacterial phylogenies based on overlapping genes
Background: Overlapping genes (OGs) in bacterial genomes are pairs of adjacent genes of which the coding sequences overlap partly or entirely. With the rapid accumulation of seque...
Yingqin Luo, Cong Fu, Da-Yong Zhang, Kui Lin