Sciweavers

72 search results - page 2 / 15
» Cost-sensitive multi-class classification from probability e...
Sort
View
KDD
2002
ACM
187views Data Mining» more  KDD 2002»
14 years 5 months ago
Transforming classifier scores into accurate multiclass probability estimates
Class membership probability estimates are important for many applications of data mining in which classification outputs are combined with other sources of information for decisi...
Bianca Zadrozny, Charles Elkan
ISMB
2001
13 years 6 months ago
Using mixtures of common ancestors for estimating the probabilities of discrete events in biological sequences
Accurately estimating probabilities from observations is important for probabilistic-based approaches to problems in computational biology. In this paper we present a biologically...
Eleazar Eskin, William Noble Grundy, Yoram Singer
JCB
2002
74views more  JCB 2002»
13 years 5 months ago
Using Substitution Matrices to Estimate Probability Distributions for Biological Sequences
Accurately estimating probabilities from observations is important for probabilistic-based approaches to problems in computational biology. In this paper we present a biologically...
Eleazar Eskin, William Stafford Noble, Yoram Singe...
AAAI
2006
13 years 6 months ago
Thresholding for Making Classifiers Cost-sensitive
In this paper we propose a very simple, yet general and effective method to make any cost-insensitive classifiers (that can produce probability estimates) cost-sensitive. The meth...
Victor S. Sheng, Charles X. Ling
ICDM
2005
IEEE
122views Data Mining» more  ICDM 2005»
13 years 11 months ago
Learning through Changes: An Empirical Study of Dynamic Behaviors of Probability Estimation Trees
In practice, learning from data is often hampered by the limited training examples. In this paper, as the size of training data varies, we empirically investigate several probabil...
Kun Zhang, Zujia Xu, Jing Peng, Bill P. Buckles