Optimizing the Gaussian kernel function with the formulated kernel target alignment criterion for two-class pattern classification

DOI10.1016/J.PATCOG.2012.12.012zbMath1296.68162OpenAlexW2085655596MaRDI QIDQ743253

Shangping Zhong, Qiaofen Xu, Daya Chen, Tianshun Chen

Publication date: 23 September 2014

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.patcog.2012.12.012

zbMATH Keywords

Euler-Maclaurin formuladetermined global minimum pointfast kernel learning methodformulated kernel target alignment criterionGaussian kernel functionhigh time efficiencytwo-class pattern classification

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items (3)

Fast Gaussian kernel learning for classification tasks based on specially structured global optimization ⋮ An efficient Gaussian kernel optimization based on centered kernel polarization criterion ⋮ Evolutionary combination of kernels for nonlinear feature transformation

Uses Software

• UCI-ml
• LIBSVM
• Delve Datasets

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Gaussian kernel optimization for pattern classification
• Euler and his work on infinite series
• Gradient-Based Adaptation of General Gaussian Kernels
• Combined SVM-based feature selection and classification

This page was built for publication: Optimizing the Gaussian kernel function with the formulated kernel target alignment criterion for two-class pattern classification