Sciweavers

4578 search results - page 347 / 916
» Learning from Multi-source Data
Sort
View
ACL
1998
15 years 5 months ago
A Connectionist Architecture for Learning to Parse
We present a connectionist architecture and demonstrate that it can learn syntactic parsing from a corpus of parsed text. The architecture can represent syntactic constituents, an...
James Henderson, Peter Lane
AIEDAM
2004
96views more  AIEDAM 2004»
15 years 3 months ago
Learning while designing
: This paper reports on preliminary results of an explorative study of a protocol analysis of team learning while designing using in-situ data. Two measurement-based frameworks are...
Gourabmoy Nath, John S. Gero
PKDD
2010
Springer
212views Data Mining» more  PKDD 2010»
15 years 2 months ago
Cross Validation Framework to Choose amongst Models and Datasets for Transfer Learning
Abstract. One solution to the lack of label problem is to exploit transfer learning, whereby one acquires knowledge from source-domains to improve the learning performance in the t...
ErHeng Zhong, Wei Fan, Qiang Yang, Olivier Versche...
ICML
2006
IEEE
16 years 4 months ago
Active sampling for detecting irrelevant features
The general approach for automatically driving data collection using information from previously acquired data is called active learning. Traditional active learning addresses the...
Sriharsha Veeramachaneni, Emanuele Olivetti, Paolo...
132
Voted
ICML
2003
IEEE
16 years 4 months ago
Finding Underlying Connections: A Fast Graph-Based Method for Link Analysis and Collaboration Queries
Many techniques in the social sciences and graph theory deal with the problem of examining and analyzing patterns found in the underlying structure and associations of a group of ...
Jeremy Kubica, Andrew W. Moore, David Cohn, Jeff G...