Robotics & Machine Learning Daily News2024,Issue(Nov.28) :63-64.

New Findings from City University of Hong Kong Describe Advances in Machine Lear ning (Validating Unsupervised Machine Learning Techniques for Software Defect Pr ediction With Generic Metamorphic Testing)

香港城市大学的新发现描述了进展机器学习(验证无监督机器学习基于泛型变形的软件缺陷诊断技术测试

Robotics & Machine Learning Daily News2024,Issue(Nov.28) :63-64.

New Findings from City University of Hong Kong Describe Advances in Machine Lear ning (Validating Unsupervised Machine Learning Techniques for Software Defect Pr ediction With Generic Metamorphic Testing)

香港城市大学的新发现描述了进展机器学习(验证无监督机器学习基于泛型变形的软件缺陷诊断技术测试

扫码查看

摘要

由一名新闻记者-机器人与机器学习日报的工作人员新闻编辑每日新闻-调查人员讨论人工智能的新发现。根据新闻报道来自香港的《中国人民报》,由NewsRx记者报道,研究称,“在软件缺陷预测,当标注的数据集很稀少时,无监督模型经常介入,尽管面对在没有数据先验知识的情况下验证模型的挑战。针对这一点,我们提出了一个一种利用通用变形测试有效验证此类模型的新方法,绕过需要E Xpert衍生的变质关系。

Abstract

By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators discuss new findings in artificial intelligence. According to news reportingfrom Hong Kong, People’s Re public of China, by NewsRx journalists, research stated, “In the realm ofsoftwa re defect prediction, unsupervised models often step in when labelled datasets a re scarce, despitefacing the challenge of validating models without prior knowl edge of data. Addressing this, we proposed anovel approach leveraging generic m etamorphic testing to validate such models effectively, bypassing theneed for e xpert-derived metamorphic relations.”

Key words

City University of Hong Kong/Hong Kong/People’s Republic of China/Asia/Cyborgs/Emerging Technologies/Machine Learn ing/Software

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文