Scholarlink

The goal of this study is to create interpretable models that may be used to improve the openness and responsibility of image-based algorithms. To make these algorithms more understandable, the research uses Support Vector Machines (SVM) together with AI methods. The goal is to make the decision-making process more understandable by connecting complicated image-based models with interpretability. This study addresses the rising demand for ethical and responsible deployment of modern technologies by contributing to the creation of more transparent and accountable image-based algorithms via the combination of SVM and AI.

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

Developing Interpretable Models to Enhance Transparency and Accountability in Image-Based Algorithms Using SVM and AI

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rampriya Kilari,
  • I. B. Ranitha,
  • Indur Ranaveer,
  • Katakam Srinivasa Rao,
  • Kummari Renuka,
  • Divya Pachimatla

摘要

The goal of this study is to create interpretable models that may be used to improve the openness and responsibility of image-based algorithms. To make these algorithms more understandable, the research uses Support Vector Machines (SVM) together with AI methods. The goal is to make the decision-making process more understandable by connecting complicated image-based models with interpretability. This study addresses the rising demand for ethical and responsible deployment of modern technologies by contributing to the creation of more transparent and accountable image-based algorithms via the combination of SVM and AI.