Scholarlink

<p>Pattern recognition models, particularly neural networks, often focus on maximising classification accuracy. However, in practice, the types of errors made (misclassification between different classes) can have varying associated costs. Current methods overlook varying misclassification error types. Misclassification labels can either be available from expert knowledge or derived from semantics of textual descriptions of class labels. Exploiting such misclassification costs can have significant implications when deploying machine learning systems. Here, using five examples from image and tabular domains, we show how a deep neural architecture trained in a nested layer-wise fashion (cascade learning) in which early layers solve easier problems than later ones could exploit such hierarchical aspects of class labels. We employ a measure of performance called “severity” of errors and show how emphasis could be placed on classes that are deeper in the hierarchy, ignoring errors that arise between semantic neighbours.</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

Balancing misclassification errors in image-based inference using problem domain semantics and a nested cascade architecture

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月13日

查看全文
  • Xin Du,
  • Rajesh Jena,
  • Katayoun Farrahi,
  • Mahesan Niranjan

摘要

Pattern recognition models, particularly neural networks, often focus on maximising classification accuracy. However, in practice, the types of errors made (misclassification between different classes) can have varying associated costs. Current methods overlook varying misclassification error types. Misclassification labels can either be available from expert knowledge or derived from semantics of textual descriptions of class labels. Exploiting such misclassification costs can have significant implications when deploying machine learning systems. Here, using five examples from image and tabular domains, we show how a deep neural architecture trained in a nested layer-wise fashion (cascade learning) in which early layers solve easier problems than later ones could exploit such hierarchical aspects of class labels. We employ a measure of performance called “severity” of errors and show how emphasis could be placed on classes that are deeper in the hierarchy, ignoring errors that arise between semantic neighbours.