机器学习的质量保证——一种功能和系统保障的方法

2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS) Pub Date : 2020-12-01 DOI:10.1109/QRS51102.2020.00016

Alexander Poth, Burkhard Meyer, Peter Schlicht, A. Riel

{"title":"机器学习的质量保证——一种功能和系统保障的方法","authors":"Alexander Poth, Burkhard Meyer, Peter Schlicht, A. Riel","doi":"10.1109/QRS51102.2020.00016","DOIUrl":null,"url":null,"abstract":"In an industrial context, high software quality is mandatory in order to avoid costly patching. We present a state of the art analysis of approaches to ensure that a specific Artificial Intelligence (AI) model is ready for release. We analyze the requirements a Machine Learning (ML) system has to fulfill in order to comply with the needs of an automotive OEM. The main implication for projects relying on ML is a holistic assessment of possible quality risks. These risks may stem from implemented ML models and spread into the delivery. We present a methodological quality assurance (QA) approach and its evaluation.","PeriodicalId":301814,"journal":{"name":"2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS)","volume":"29 5","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":"{\"title\":\"Quality Assurance for Machine Learning – an approach to function and system safeguarding\",\"authors\":\"Alexander Poth, Burkhard Meyer, Peter Schlicht, A. Riel\",\"doi\":\"10.1109/QRS51102.2020.00016\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In an industrial context, high software quality is mandatory in order to avoid costly patching. We present a state of the art analysis of approaches to ensure that a specific Artificial Intelligence (AI) model is ready for release. We analyze the requirements a Machine Learning (ML) system has to fulfill in order to comply with the needs of an automotive OEM. The main implication for projects relying on ML is a holistic assessment of possible quality risks. These risks may stem from implemented ML models and spread into the delivery. We present a methodological quality assurance (QA) approach and its evaluation.\",\"PeriodicalId\":301814,\"journal\":{\"name\":\"2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS)\",\"volume\":\"29 5\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"13\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/QRS51102.2020.00016\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/QRS51102.2020.00016","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 13

摘要

在工业环境中，为了避免昂贵的补丁，高软件质量是强制性的。我们提出了一种最先进的方法分析，以确保特定的人工智能(AI)模型准备发布。我们分析了机器学习(ML)系统必须满足的要求，以满足汽车OEM的需求。依赖ML的项目的主要含义是对可能的质量风险进行全面评估。这些风险可能源于实现的ML模型，并扩散到交付中。我们提出了一种方法学的质量保证(QA)方法及其评价。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Quality Assurance for Machine Learning – an approach to function and system safeguarding

In an industrial context, high software quality is mandatory in order to avoid costly patching. We present a state of the art analysis of approaches to ensure that a specific Artificial Intelligence (AI) model is ready for release. We analyze the requirements a Machine Learning (ML) system has to fulfill in order to comply with the needs of an automotive OEM. The main implication for projects relying on ML is a holistic assessment of possible quality risks. These risks may stem from implemented ML models and spread into the delivery. We present a methodological quality assurance (QA) approach and its evaluation.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2020 IEEE 20th International Conference on Software Quality, Reliability and Security (QRS)

自引率

0.00%

发文量