An improved error-correcting output coding framework with kernel-based decoding

Authors:
Dijun Luo;Rong Xiong
Affiliations:
Computer Science and Engineering Department, University of Texas at Arlington, 701 S. Nedderman Drive, Arlington, TX 76019, USA;State Key Laboratory of Industrial Control Technology, Zhejiang University, Zheda Road, Hangzhou, Zhejiang 310027, China
Venue:
Neurocomputing
Year:
2008

Citing 11
Cited 3

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
C4.5: programs for machine learning

C4.5: programs for machine learning
Support-Vector Networks

Machine Learning
Classification by pairwise coupling

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
On the Learnability and Design of Output Codes for Multiclass Problems

Machine Learning
Using output codes to boost multiclass learning problems

ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Optimizing search engines using clickthrough data

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Reducing multiclass to binary: a unifying approach for margin classifiers

The Journal of Machine Learning Research
Solving multiclass learning problems via error-correcting output codes

Journal of Artificial Intelligence Research
A comparison of methods for multiclass support vector machines

IEEE Transactions on Neural Networks
New results on error correcting output codes of kernel machines

IEEE Transactions on Neural Networks

Improving multiclass text classification with error-correcting output coding and sub-class partitions

AI'10 Proceedings of the 23rd Canadian conference on Advances in Artificial Intelligence
Can under-exploited structure of original-classes help ECOC-based multi-class classification?

Neurocomputing
Solving multi-class problems by data-driven topology-preserving output codes

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a novel framework of error-correcting output coding (ECOC) addressing the problem of multi-class classification. By weighting the output space of each base classifier which is trained independently, the distance function of decoding is adapted so that the samples are more discriminative. A criterion generated over the Extended Pair Samples (EPS) is proposed to train the weights of output space. We first conduct empirical studies on UCI datasets to verify the presented framework with four frequently used coding matrixes and then apply it in RoboCup domain to enhance the performance of agent control. Color-based image segmentation is also tested in this paper. Experimental results show that our supervised learned decoding scheme improves the accuracy of classification significantly and betters the ball control of agents in a soccer game after learning from experience. Some properties still hold in the new framework: any classifier, as well as distance function, is still applicable. Besides, it is allowed in the new framework to implement nonlinear decoding processes using kernel tricks.