Reference : Specifying key-properties to improve the recognition skills of neural networks
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/44492
Specifying key-properties to improve the recognition skills of neural networks
English
Jahic, Benjamin mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
Guelfi, Nicolas mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
Ries, Benoit mailto [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS) >]
6-Nov-2020
Proceedings of the 2020 European Symposium on Software Engineering
Association for Computing Machinery
Yes
International
9781450377621
New York
United States
2020 European Symposium on Software Engineering
from 06-11-2020 to 08-11-2020
[en] Software engineering ; methods ; neural networks ; specifications ; key-properties ; dataset augmentation
[en] Software engineers are increasingly asked to build datasets for engineering neural network-based software systems. These datasets are used to train neural networks to recognise data. Traditionally, data scientists build datasets consisting of random collected or generated data. Their approaches are often costly, inefficient and time-consuming. Software engineers rely on these traditional approaches that do not support precise data selection criteria based on customer’s requirements. In this paper, we introduce an extended software engineering method for dataset augmentation to improve neural networks by satisfying the customer’s requirements. We introduce the notion of key-properties to describe the neural network’s recognition skills. Key-properties are used all along the engineering process for developing the neural network in cooperation with the customer. We propose a rigorous process for augmenting datasets based on the analysis and specification of the key-properties. We conducted an experimentation on a case study on the recognition of the state of a digital meter counter. We demonstrate an informal specification of the neural network’s key-properties and a successful improvement of a neural network’s recognition of the meter counter state.
Researchers
http://hdl.handle.net/10993/44492
10.1145/3393822.3432332

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
2020-esse-keypropertiespecification-published.pdfPublisher postprint1.24 MBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.