Sciweavers

80 search results - page 4 / 16
» On the Learnability and Design of Output Codes for Multiclas...
Sort
View
PR
2008
154views more  PR 2008»
13 years 7 months ago
Data-driven decomposition for multi-class classification
This paper presents a new study on a method of designing a multi-class classifier: Data-driven Error Correcting Output Coding (DECOC). DECOC is based on the principle of Error Cor...
Jie Zhou, Hanchuan Peng, Ching Y. Suen
PRL
2008
133views more  PRL 2008»
13 years 7 months ago
Better multiclass classification via a margin-optimized single binary problem
We develop a new multiclass classification method that reduces the multiclass problem to a single binary classifier (SBC). Our method constructs the binary problem by embedding sm...
Ran El-Yaniv, Dmitry Pechyony, Elad Yom-Tov
ICPR
2006
IEEE
14 years 8 months ago
Forest Extension of Error Correcting Output Codes and Boosted Landmarks
In this paper, we introduce a robust novel approach for detecting objects category in cluttered scenes by generating boosted contextual descriptors of landmarks. In particular, ou...
Oriol Pujol, Petia Radeva, Sergio Escalera
ESANN
2007
13 years 9 months ago
Ensemble neural classifier design for face recognition
A method for tuning MLP learning parameters in an ensemble classifier framework is presented. No validation set or cross-validation technique is required to optimize parameters for...
Terry Windeatt
NIPS
2000
13 years 9 months ago
Improved Output Coding for Classification Using Continuous Relaxation
Output coding is a general method for solving multiclass problems by reducing them to multiple binary classification problems. Previous research on output coding has employed, alm...
Koby Crammer, Yoram Singer