Sciweavers

65 search results - page 2 / 13
» Third-order generalization: A new approach to categorizing h...
Sort
View
IJON
2008
73views more  IJON 2008»
13 years 5 months ago
Third-order generalization: A new approach to categorizing higher-order generalization
Generalization, in its most basic form, is an artificial neural network's (ANN's) ability to automatically classify data that were not seen during training. This paper p...
Richard Neville
COLT
2007
Springer
13 years 12 months ago
Prediction by Categorical Features: Generalization Properties and Application to Feature Ranking
We describe and analyze a new approach for feature ranking in the presence of categorical features with a large number of possible values. It is shown that popular ranking criteria...
Sivan Sabato, Shai Shalev-Shwartz
JMLR
2008
111views more  JMLR 2008»
13 years 5 months ago
Ranking Categorical Features Using Generalization Properties
Feature ranking is a fundamental machine learning task with various applications, including feature selection and decision tree learning. We describe and analyze a new feature ran...
Sivan Sabato, Shai Shalev-Shwartz
SIGPRO
2008
130views more  SIGPRO 2008»
13 years 5 months ago
Cepstrum of bispectrum - A new approach to blind system reconstruction
In this paper, an improved approach to blind deconvolution of LTI systems incorporating phase unwrapping is presented. The method can recover a noise-free estimate of the logarith...
Shahjahan Shahid, Jacqueline Walker
CVPR
2012
IEEE
11 years 8 months ago
A codebook-free and annotation-free approach for fine-grained image categorization
Fine-grained categorization refers to the task of classifying objects that belong to the same basic-level class (e.g. different bird species) and share similar shape or visual app...
Bangpeng Yao, Gary R. Bradski, Fei-Fei Li