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

被引：9

作者：

Poth, Alexander ^{[1
]}

Meyer, Burkhard ^{[2
]}

Schlicht, Peter ^{[1
]}

Riel, Andreas ^{[3
]}

机构：

[1] Volkswagen AG, Wolfsburg, Germany

[2] Audi AG, Ingolstadt, Germany

[3] Grenoble Alps Univ, Grenoble, France

来源：

2020 IEEE 20TH INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY, AND SECURITY (QRS 2020) | 2020年

关键词：

artificial intelligence; machine learning; quality management; quality assurance; risk management;

D O I：

10.1109/QRS51102.2020.00016

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

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.

引用

页码：22 / 29

页数：8

共 26 条

[1] [Anonymous], 2016, NEURAL INFORM PROCES
[2] Basu S., 2018, IEEE DESIGN TEST 201
[3] Cai Shanqing, 2016, Tensorflow debugger: Debugging dataflow graphs for machine learning
[4] Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition
Dahl, George E.
Yu, Dong
Deng, Li
Acero, Alex
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2012, 20 (01): : 30 - 42
[5] Evtimov I., 2018, ROBUST PHYS WORLD AT
[6] Serving deep learning models in a serverless platform
Ishakian, Vatche
Muthusamy, Vinod
Slominski, Aleksander
[J]. 2018 IEEE INTERNATIONAL CONFERENCE ON CLOUD ENGINEERING (IC2E 2018), 2018, : 257 - 262
[7] Kurakin Alexey, 2016, ARXIV161101236
[8] Mansour Y., 2016, NEURAL INFORM PROCES
[9] Verification and validation and artificial intelligence
Menzies, T
Pecheur, C
[J]. ADVANCES IN COMPUTERS, VOL 65, 2005, 65 : 153 - +
[10] Murphy C., 2007, An Approach to Software Testing of Machine Learning Applications'

← 1 2 3 →