Logic-based learning in software engineering

File Description SizeFormat 
mainpage.pdfAccepted version139.7 kBAdobe PDFDownload
Title: Logic-based learning in software engineering
Author(s): Alrajeh, D
Russo, A
Uchitel, S
Kramer, J
Item Type: Conference Paper
Abstract: In recent years, research efforts have been directed towards the use of Machine Learning (ML) techniques to support and automate activities such as program repair, specification mining and risk assessment. The focus has largely been on techniques for classification, clustering and regression. Although beneficial, these do not produce a declarative, interpretable representation of the learned information. Hence, they cannot readily be used to inform, revise and elaborate software models. On the other hand, recent advances in ML have witnessed the emergence of new logic-based learning approaches that differ from traditional ML in that their output is represented in a declarative, rule-based manner, making them well-suited for many software engineering tasks. In this technical briefing, we will introduce the audience to the latest advances in logic-based learning, give an overview of how logic-based learning systems can successfully provide automated support to a variety of software engineering tasks, demonstrate the application to two real case studies from the domain of requirements engineering and software design and highlight future challenges and directions.
Publication Date: 14-May-2016
Date of Acceptance: 14-May-2016
URI: http://hdl.handle.net/10044/1/53065
DOI: https://dx.doi.org/10.1145/2889160.2891050
Publisher: IEEE
Start Page: 892
End Page: 893
Journal / Book Title: ICSE '16 Proceedings of the 38th International Conference on Software Engineering Companion
Copyright Statement: © 2016 Copyright held by the owner/author(s). Published by ACM.
Conference Name: 38th IEEE/ACM International Conference on Software Engineering Companion (ICSE)
Keywords: Science & Technology
Technology
Computer Science, Software Engineering
Computer Science
DEFECT PREDICTION
Science & Technology
Technology
Computer Science, Software Engineering
Computer Science
DEFECT PREDICTION
Publication Status: Published
Start Date: 2016-05-14
Finish Date: 2016-05-22
Conference Place: Austin, TX
Appears in Collections:Faculty of Engineering
Computing



Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons