Sciweavers

1090 search results - page 43 / 218
» Consistency measures for feature selection
Sort
View
NIPS
2004
13 years 10 months ago
The Laplacian PDF Distance: A Cost Function for Clustering in a Kernel Feature Space
A new distance measure between probability density functions (pdfs) is introduced, which we refer to as the Laplacian pdf distance. The Laplacian pdf distance exhibits a remarkabl...
Robert Jenssen, Deniz Erdogmus, José Carlos...
ACCV
1998
Springer
14 years 1 months ago
Optimising the Complete Image Feature Extraction Chain
The hypothesis veri cation stage of the traditional image processing approach, consisting of low, medium, and high level processing, will su er if the set of low level features ext...
Majid Mirmehdi, Phil L. Palmer, Josef Kittler
IDA
2002
Springer
13 years 8 months ago
Evolutionary model selection in unsupervised learning
Feature subset selection is important not only for the insight gained from determining relevant modeling variables but also for the improved understandability, scalability, and pos...
YongSeog Kim, W. Nick Street, Filippo Menczer
ICCBR
2007
Springer
14 years 3 months ago
Catching the Drift: Using Feature-Free Case-Based Reasoning for Spam Filtering
In this paper, we compare case-based spam filters, focusing on their resilience to concept drift. In particular, we evaluate how to track concept drift using a case-based spam fi...
Sarah Jane Delany, Derek G. Bridge
BMVC
2002
13 years 11 months ago
Texture classification with thousands of features
The Trace transform is a generalisation of the Radon transform that allows one to construct image features that do not necessarily have meaning in terms of human perception, but t...
Alexander Kadyrov, A. Talepbour, Maria Petrou