Sciweavers

1400 search results - page 115 / 280
» Post-Analysis of Learned Rules
Sort
View
ICML
2010
IEEE
15 years 5 months ago
Risk minimization, probability elicitation, and cost-sensitive SVMs
A new procedure for learning cost-sensitive SVM classifiers is proposed. The SVM hinge loss is extended to the cost sensitive setting, and the cost-sensitive SVM is derived as the...
Hamed Masnadi-Shirazi, Nuno Vasconcelos
GECCO
2007
Springer
148views Optimization» more  GECCO 2007»
15 years 10 months ago
Fuzzy-UCS: preliminary results
This paper presents Fuzzy-UCS, a Michigan-style Learning Fuzzy-Classifier System designed for supervised learning tasks. Fuzzy-UCS combines the generalization capabilities of UCS...
Albert Orriols-Puig, Jorge Casillas, Ester Bernad&...
ICML
2008
IEEE
16 years 5 months ago
Laplace maximum margin Markov networks
We propose Laplace max-margin Markov networks (LapM3 N), and a general class of Bayesian M3 N (BM3 N) of which the LapM3 N is a special case with sparse structural bias, for robus...
Jun Zhu, Eric P. Xing, Bo Zhang
ICDM
2005
IEEE
118views Data Mining» more  ICDM 2005»
15 years 10 months ago
A Heterogeneous Field Matching Method for Record Linkage
Record linkage is the process of determining that two records refer to the same entity. A key subprocess is evaluating how well the individual fields, or attributes, of the recor...
Steven Minton, Claude Nanjo, Craig A. Knoblock, Ma...
IJCAI
2007
15 years 5 months ago
Ensembles of Partially Trained SVMs with Multiplicative Updates
The training of support vector machines (SVM) involves a quadratic programming problem, which is often optimized by a complicated numerical solver. In this paper, we propose a muc...
Ivor W. Tsang, James T. Kwok