Conformal transformation of kernel functions: A data-dependent way to improve support vector machine classifiers

DOI10.1023/A:1013848912046MaRDI QIDQ1857729zbMATH OpenOpenAlexFDO

Authors Si Wu, Shun-Ichi Amari

Publication date 19 February 2003

Published in Neural Processing Letters (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1023/a:1013848912046

zbMATH Keywords

kernel functionpattern recognitionRiemannian geometry and conformal transformationsupport vector machine

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Advances in Neural Networks – ISNN 2005
• Automatic model selection method for support vector machines classifiers
• Automatic model selection method for support vector machines classifiers
• An iterative modified kernel based on training data
• Adaptive kernels for support vector classification

Cited in

(13)

• An iterative modified kernel based on training data
• Dynamics and architecture for neural computation
• A multikernel-like learning algorithm based on data probability distribution
• The geometric structure on a degradation model with application to optimal design under a cost constraint
• Amari-Chentsov structure on the statistical manifold of models for accelerated life tests
• Detecting direct associations in a network by information theoretic approaches
• Scaling the kernel function based on the separating boundary in input space: a data-dependent way for improving the performance of kernel methods
• Support vector machines with applications
• Adaptive kernel scaling support vector machine with application to a prostate cancer image study
• Advances in Neural Networks – ISNN 2005
• Rejoinder
• Lowest probability mass neighbour algorithms: relaxing the metric constraint in distance-based neighbourhood algorithms
• Conformal transformation of kernels: a geometric perspective on text classification

This page was built for publication: Conformal transformation of kernel functions: A data-dependent way to improve support vector machine classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1857729)