Reusability in artificial neural networks: An empirical study

Javad Ghofrani, Ehsan Kozegar, Arezoo Bozorgmehr, Mohammad Divband Soorati

Abstract

Machine learning, especially deep learning has aroused interests of researchers and practitioners for the last few years in development of intelligent systems such as speech, natural language, and image processing. Software solutions based on machine learning techniques attract more attention as alternatives to conventional software systems. In this paper, we investigate how reusability techniques are applied in implementation of artificial neural networks (ANNs). We conducted an empirical study with an online survey among experts with experience in developing solutions with ANNs. We analyze the feedback ofmore than 100 experts to our survey. The results show existing challenges and some of the applied solutions in an intersection between reusability and ANNs.

OriginalspracheEnglisch
TitelSPLC '19: Proceedings of the 23rd International Systems and Software Product Line Conference
Redakteure/-innenCarlos Cetina, Oscar Díaz, Laurence Duchien, Marianne Huchard, Rick Rabiser, Camille Salinesi, Christoph Seidl, Xhevahire Tërnava, Leopoldo Teixeira, Thomas Thüm, Tewfik Ziadi
Seitenumfang8
BandB
Herausgeber (Verlag)ACM
Erscheinungsdatum09.09.2019
Seiten122–129
ISBN (Print)978-1-4503-6668-7
DOIs
PublikationsstatusVeröffentlicht - 09.09.2019
Veranstaltung23rd International Systems and Software Product Line Conference - Paris, Frankreich
Dauer: 09.09.201913.09.2019
Konferenznummer: 154713

Fingerprint

Untersuchen Sie die Forschungsthemen von „Reusability in artificial neural networks: An empirical study“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren