Sciweavers

986 search results - page 48 / 198
» Zero-data Learning of New Tasks
Sort
View
KDD
2010
ACM
274views Data Mining» more  KDD 2010»
15 years 1 months ago
Grafting-light: fast, incremental feature selection and structure learning of Markov random fields
Feature selection is an important task in order to achieve better generalizability in high dimensional learning, and structure learning of Markov random fields (MRFs) can automat...
Jun Zhu, Ni Lao, Eric P. Xing
NIPS
1997
14 years 11 months ago
Using Expectation to Guide Processing: A Study of Three Real-World Applications
In many real world tasks, only a small fraction of the available inputs are important at any particular time. This paper presents a method for ascertaining the relevance of inputs...
Shumeet Baluja
ECTEL
2007
Springer
15 years 4 months ago
Categorizing Learning Objects Based On Wikipedia as Substitute Corpus
As metadata is often not sufficiently provided by authors of Learning Resources, automatic metadata generation methods are used to create metadata afterwards. One kind of metadata ...
Marek Meyer, Christoph Rensing, Ralf Steinmetz
FLAIRS
2008
15 years 4 days ago
Learning in the Lexical-Grammatical Interface
Children are facile at both discovering word boundaries and using those words to build higher-level structures in tandem. Current research treats lexical acquisition and grammar i...
Tom Armstrong, Tim Oates
JASIS
2006
96views more  JASIS 2006»
14 years 9 months ago
Learning to classify documents according to genre
Genre or style analysis can be used to improve results achieved using standard IR techniques. A genre class is a group of documents that are written in a similar style. Genre clas...
Aidan Finn, Nicholas Kushmerick