Sciweavers

SDM
2010
SIAM
218views Data Mining» more  SDM 2010»
13 years 6 months ago
Confidence-Based Feature Acquisition to Minimize Training and Test Costs
We present Confidence-based Feature Acquisition (CFA), a novel supervised learning method for acquiring missing feature values when there is missing data at both training and test...
Marie desJardins, James MacGlashan, Kiri L. Wagsta...
ICDM
2002
IEEE
70views Data Mining» more  ICDM 2002»
13 years 9 months ago
Progressive Modeling
Presently, inductive learning is still performed in a frustrating batch process. The user has little interaction with the system and no control over the final accuracy and traini...
Wei Fan, Haixun Wang, Philip S. Yu, Shaw-hwa Lo, S...
PKDD
2005
Springer
142views Data Mining» more  PKDD 2005»
13 years 10 months ago
Speeding Up Logistic Model Tree Induction
Logistic Model Trees have been shown to be very accurate and compact classifiers [8]. Their greatest disadvantage is the computational complexity of inducing the logistic regressi...
Marc Sumner, Eibe Frank, Mark A. Hall
IJCNN
2006
IEEE
13 years 10 months ago
Online Training of a Generalized Neuron with Particle Swarm Optimization
— Neural networks are used in a wide number of fields including signal and image processing, modeling and control and pattern recognition. Some of the most common type of neural ...
Raveesh Kiran, Sandhya R. Jetti, Ganesh K. Venayag...