Two Criteria for Model Selection in Multiclass Support Vector Machines

Abstract--Practical applications call for efficient model selection criteria for multiclass support vector machine (SVM) classification. To solve this problem, this paper develops two model selection criteria by combining or redefining the radius

• Type: Journal
• Year: 2008
• Where: TSMC
• Authors: Lei Wang, Ping Xue, Kap Luk Chan
• Keywords: Binary Svms, Model Selection, Model Selection Criteria, TSMC 2008