Scholarlink

<p>A new kernel machine for multi-class pattern recognition is introduced: the isotropic kernel machine. It is designed to make use of the isotropy of the class conditional densities in the feature space. We provide theoretical guarantees on its generalization error. This error is then assessed empirically, in the framework of a comparative study.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Isotropic Kernel Machine

  • 期刊论文

  • 发表日期：

    2025年5月6日

查看全文
  • Yann Guermeur,
  • Nicolas Wicker

摘要

A new kernel machine for multi-class pattern recognition is introduced: the isotropic kernel machine. It is designed to make use of the isotropy of the class conditional densities in the feature space. We provide theoretical guarantees on its generalization error. This error is then assessed empirically, in the framework of a comparative study.