Sciweavers

2295 search results - page 386 / 459
» Learning Overcomplete Representations
Sort
View
FLAIRS
2010
14 years 10 days ago
Handling of Numeric Ranges for Graph-Based Knowledge Discovery
Nowadays, graph-based knowledge discovery algorithms do not consider numeric attributes (they are discarded in the preprocessing step, or they are treated as alphanumeric values w...
Oscar E. Romero, Jesus A. Gonzalez, Lawrence B. Ho...
ECCV
2008
Springer
13 years 11 months ago
Unsupervised Classification and Part Localization by Consistency Amplification
We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
Leonid Karlinsky, Michael Dinerstein, Dan Levi, Sh...
ICMLA
2007
13 years 11 months ago
Understanding Challenges in Preserving and Reconstructing Computer-Assisted Medical Decision Processes
— This paper addresses the problem of understanding preservation and reconstruction requirements for computeraided medical decision-making. With an increasing number of computer-...
Sang-Chul Lee, Peter Bajcsy
COLING
2000
13 years 11 months ago
Language Identification In Unknown Signals
This paper describes algorithms and software developed to characterise and detect generic intelligent language-like features iu an input signal, using Natural Language Learning te...
John R. Elliott, Eric Atwell, Bill Whyte
BMCBI
2010
186views more  BMCBI 2010»
13 years 10 months ago
Knowledge-based biomedical word sense disambiguation: comparison of approaches
Background: Word sense disambiguation (WSD) algorithms attempt to select the proper sense of ambiguous terms in text. Resources like the UMLS provide a reference thesaurus to be u...
Antonio Jimeno Yepes, Alan R. Aronson