Sciweavers

235 search results - page 14 / 47
» Constructing New and Better Evaluation Measures for Machine ...
Sort
View
NIPS
2007
14 years 11 months ago
Transfer Learning using Kolmogorov Complexity: Basic Theory and Empirical Evaluations
In transfer learning we aim to solve new problems using fewer examples using information gained from solving related problems. Transfer learning has been successful in practice, a...
M. M. Mahmud, Sylvian R. Ray
DMIN
2009
142views Data Mining» more  DMIN 2009»
14 years 7 months ago
A Combinatorial Fusion Method for Feature Construction
- This paper demonstrates how methods borrowed from information fusion can improve the performance of a classifier by constructing (i.e., fusing) new features that are combinations...
Ye Tian, Gary M. Weiss, D. Frank Hsu, Qiang Ma
65
Voted
ICML
2003
IEEE
15 years 10 months ago
Margin Distribution and Learning
Recent theoretical results have shown that improved bounds on generalization error of classifiers can be obtained by explicitly taking the observed margin distribution of the trai...
Ashutosh Garg, Dan Roth
ICML
2004
IEEE
15 years 10 months ago
Learning large margin classifiers locally and globally
A new large margin classifier, named MaxiMin Margin Machine (M4 ) is proposed in this paper. This new classifier is constructed based on both a "local" and a "globa...
Kaizhu Huang, Haiqin Yang, Irwin King, Michael R. ...
86
Voted
ICCV
2009
IEEE
16 years 1 months ago
Sparsity Induced Similarity Measure for Label Propagation
Graph-based semi-supervised learning has gained considerable interests in the past several years thanks to its effectiveness in combining labeled and unlabeled data through labe...
Hong Cheng, Zicheng Liu, Jie Yang