Coded output support vector machine

Authors:
Tao Ye;Xuefeng Zhu
Affiliations:
College of Automation Science and Engineering, South China University of Technology, Guangzhou, P.R. China;College of Automation Science and Engineering, South China University of Technology, Guangzhou, P.R. China
Venue:
ICIC'12 Proceedings of the 8th international conference on Intelligent Computing Theories and Applications
Year:
2012

Citing 14
Cited 0

A training algorithm for optimal margin classifiers

COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning
Making large-scale support vector machine learning practical

Advances in kernel methods
Least Squares Support Vector Machine Classifiers

Neural Processing Letters
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
A Tutorial on Support Vector Machines for Pattern Recognition

Data Mining and Knowledge Discovery
A tutorial on support vector regression

Statistics and Computing
New Support Vector Algorithms

Neural Computation
A Parallel Implementation of Error Correction SVM with Applications to Face Recognition

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Solving multiclass learning problems via error-correcting output codes

Journal of Artificial Intelligence Research
The bridge relating process neural networks and traditional neural networks

Neurocomputing
Mixture of SVMs for face class modeling

MLMI'04 Proceedings of the First international conference on Machine Learning for Multimodal Interaction
An overview of statistical learning theory

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

The authors propose a coded output support vector machine (COSVM) by introducing the idea of information coding to solve multi-class classification problems for large-scale datasets. The COSVM is built based on the support vector regression (SVR) machine that is implemented by the sequential minimal optimization (SMO) algorithm. The paper first introduces the soft ε-tube SVR's basic principles, next shows the idea and procedure of the SMO algorithm, and then gives the idea and topology of the COSVM. To study a number system's (NS) impact on the COSVM's performance, three experiments are performed with the Character Trajectories dataset, in which output labels are coded with the natural NS, decimal NS, and binary NS, respectively. Some useful results are obtained in these experiments. The final section concludes the paper and gives some further research visions.