Scholarlink

<p>The outstanding performance of deep neural networks and machine learning algorithms is driving widespread adoption of these technologies across various application domains, including safety-critical systems like self-driving cars, autonomous robots, and medical diagnostic support systems. However, most deep learning models were not designed to guarantee safe, secure, and predictable behavior. Hence, several challenges must be addressed at multiple architectural levels to ensure their reliability and trustworthiness. This paper discusses some key issues related to AI-powered embedded systems, proposing potential solutions and research directions aimed at enhancing their security, safety, and predictability.</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

Toward predictable AI-based real-time systems

  • 期刊论文

  • 发表日期：

    2025年6月5日

查看全文
  • Giorgio Buttazzo

摘要

The outstanding performance of deep neural networks and machine learning algorithms is driving widespread adoption of these technologies across various application domains, including safety-critical systems like self-driving cars, autonomous robots, and medical diagnostic support systems. However, most deep learning models were not designed to guarantee safe, secure, and predictable behavior. Hence, several challenges must be addressed at multiple architectural levels to ensure their reliability and trustworthiness. This paper discusses some key issues related to AI-powered embedded systems, proposing potential solutions and research directions aimed at enhancing their security, safety, and predictability.