Applying product line engineering concepts to deep neural networks

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autoren

  • Javad Ghofrani
  • Ehsan Kozegar
  • Anna Lena Fehlhaber
  • Mohammad Divband Soorati

Organisationseinheiten

Externe Organisationen

  • Hochschule für Technik und Wirtschaft Dresden (FH)
  • Guilan University
  • Universität zu Lübeck
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksSPLC 2019
Untertitel23rd International Systems and Software Product Line Conference
Herausgeber/-innenThorsten Berger, Philippe Collet, Laurence Duchien, Thomas Fogdal, Patrick Heymans, Timo Kehrer, Jabier Martinez, Raul Mazo, Leticia Montalvillo, Camille Salinesi, Xhevahire Ternava, Thomas Thum, Tewfik Ziadi
ErscheinungsortNew York
Herausgeber (Verlag)Association for Computing Machinery (ACM)
Seiten72-77
Seitenumfang6
ISBN (elektronisch)9781450371384
PublikationsstatusVeröffentlicht - 9 Sept. 2019
Veranstaltung23rd International Software Product Line Conference, SPLC 2019 - Paris, Frankreich
Dauer: 9 Sept. 201913 Sept. 2019

Publikationsreihe

NameACM International Conference Proceeding Series (ICPS)
BandA

Abstract

Deep Neural Networks (DNNs) are increasingly being used as a machine learning solution thanks to the complexity of their architecture and hyperparameters-weights. A drawback is the excessive demand for massive computational power during the training process. Not only as a whole but parts of neural networks can also be in charge of certain functionalities. We present a novel challenge in an intersection between machine learning and variability management communities to reuse modules of DNNs without further training. Let us assume that we are given a DNN for image processing that recognizes cats and dogs. By extracting a part of the network, without additional training a new DNN should be divisible with the functionality of recognizing only cats. Existing research in variability management can offer a foundation for a product line of DNNs composing the reusable functionalities. An ideal solution can be evaluated based on its speed, granularity of determined functionalities, and the support for adding variability to the network. The challenge is decomposed in three subchallenges: feature extraction, feature abstraction, and the implementation of a product line of DNNs.

ASJC Scopus Sachgebiete

Zitieren

Applying product line engineering concepts to deep neural networks. / Ghofrani, Javad; Kozegar, Ehsan; Fehlhaber, Anna Lena et al.
SPLC 2019 : 23rd International Systems and Software Product Line Conference. Hrsg. / Thorsten Berger; Philippe Collet; Laurence Duchien; Thomas Fogdal; Patrick Heymans; Timo Kehrer; Jabier Martinez; Raul Mazo; Leticia Montalvillo; Camille Salinesi; Xhevahire Ternava; Thomas Thum; Tewfik Ziadi. New York: Association for Computing Machinery (ACM), 2019. S. 72-77 (ACM International Conference Proceeding Series (ICPS); Band A).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Ghofrani, J, Kozegar, E, Fehlhaber, AL & Soorati, MD 2019, Applying product line engineering concepts to deep neural networks. in T Berger, P Collet, L Duchien, T Fogdal, P Heymans, T Kehrer, J Martinez, R Mazo, L Montalvillo, C Salinesi, X Ternava, T Thum & T Ziadi (Hrsg.), SPLC 2019 : 23rd International Systems and Software Product Line Conference. ACM International Conference Proceeding Series (ICPS), Bd. A, Association for Computing Machinery (ACM), New York, S. 72-77, 23rd International Software Product Line Conference, SPLC 2019, Paris, Frankreich, 9 Sept. 2019. https://doi.org/10.1145/3336294.3336321
Ghofrani, J., Kozegar, E., Fehlhaber, A. L., & Soorati, M. D. (2019). Applying product line engineering concepts to deep neural networks. In T. Berger, P. Collet, L. Duchien, T. Fogdal, P. Heymans, T. Kehrer, J. Martinez, R. Mazo, L. Montalvillo, C. Salinesi, X. Ternava, T. Thum, & T. Ziadi (Hrsg.), SPLC 2019 : 23rd International Systems and Software Product Line Conference (S. 72-77). (ACM International Conference Proceeding Series (ICPS); Band A). Association for Computing Machinery (ACM). https://doi.org/10.1145/3336294.3336321
Ghofrani J, Kozegar E, Fehlhaber AL, Soorati MD. Applying product line engineering concepts to deep neural networks. in Berger T, Collet P, Duchien L, Fogdal T, Heymans P, Kehrer T, Martinez J, Mazo R, Montalvillo L, Salinesi C, Ternava X, Thum T, Ziadi T, Hrsg., SPLC 2019 : 23rd International Systems and Software Product Line Conference. New York: Association for Computing Machinery (ACM). 2019. S. 72-77. (ACM International Conference Proceeding Series (ICPS)). doi: 10.1145/3336294.3336321
Ghofrani, Javad ; Kozegar, Ehsan ; Fehlhaber, Anna Lena et al. / Applying product line engineering concepts to deep neural networks. SPLC 2019 : 23rd International Systems and Software Product Line Conference. Hrsg. / Thorsten Berger ; Philippe Collet ; Laurence Duchien ; Thomas Fogdal ; Patrick Heymans ; Timo Kehrer ; Jabier Martinez ; Raul Mazo ; Leticia Montalvillo ; Camille Salinesi ; Xhevahire Ternava ; Thomas Thum ; Tewfik Ziadi. New York : Association for Computing Machinery (ACM), 2019. S. 72-77 (ACM International Conference Proceeding Series (ICPS)).
Download
@inproceedings{18648577e24f44afb46d6aa7f1dd1dde,
title = "Applying product line engineering concepts to deep neural networks",
abstract = "Deep Neural Networks (DNNs) are increasingly being used as a machine learning solution thanks to the complexity of their architecture and hyperparameters-weights. A drawback is the excessive demand for massive computational power during the training process. Not only as a whole but parts of neural networks can also be in charge of certain functionalities. We present a novel challenge in an intersection between machine learning and variability management communities to reuse modules of DNNs without further training. Let us assume that we are given a DNN for image processing that recognizes cats and dogs. By extracting a part of the network, without additional training a new DNN should be divisible with the functionality of recognizing only cats. Existing research in variability management can offer a foundation for a product line of DNNs composing the reusable functionalities. An ideal solution can be evaluated based on its speed, granularity of determined functionalities, and the support for adding variability to the network. The challenge is decomposed in three subchallenges: feature extraction, feature abstraction, and the implementation of a product line of DNNs.",
keywords = "Deep neural networks, Machine learning, Software product lines, Transfer learning, Variability",
author = "Javad Ghofrani and Ehsan Kozegar and Fehlhaber, {Anna Lena} and Soorati, {Mohammad Divband}",
year = "2019",
month = sep,
day = "9",
doi = "10.1145/3336294.3336321",
language = "English",
series = "ACM International Conference Proceeding Series (ICPS)",
publisher = "Association for Computing Machinery (ACM)",
pages = "72--77",
editor = "Thorsten Berger and Philippe Collet and Laurence Duchien and Thomas Fogdal and Patrick Heymans and Timo Kehrer and Jabier Martinez and Raul Mazo and Leticia Montalvillo and Camille Salinesi and Xhevahire Ternava and Thomas Thum and Tewfik Ziadi",
booktitle = "SPLC 2019",
address = "United States",
note = "23rd International Software Product Line Conference, SPLC 2019 ; Conference date: 09-09-2019 Through 13-09-2019",

}

Download

TY - GEN

T1 - Applying product line engineering concepts to deep neural networks

AU - Ghofrani, Javad

AU - Kozegar, Ehsan

AU - Fehlhaber, Anna Lena

AU - Soorati, Mohammad Divband

PY - 2019/9/9

Y1 - 2019/9/9

N2 - Deep Neural Networks (DNNs) are increasingly being used as a machine learning solution thanks to the complexity of their architecture and hyperparameters-weights. A drawback is the excessive demand for massive computational power during the training process. Not only as a whole but parts of neural networks can also be in charge of certain functionalities. We present a novel challenge in an intersection between machine learning and variability management communities to reuse modules of DNNs without further training. Let us assume that we are given a DNN for image processing that recognizes cats and dogs. By extracting a part of the network, without additional training a new DNN should be divisible with the functionality of recognizing only cats. Existing research in variability management can offer a foundation for a product line of DNNs composing the reusable functionalities. An ideal solution can be evaluated based on its speed, granularity of determined functionalities, and the support for adding variability to the network. The challenge is decomposed in three subchallenges: feature extraction, feature abstraction, and the implementation of a product line of DNNs.

AB - Deep Neural Networks (DNNs) are increasingly being used as a machine learning solution thanks to the complexity of their architecture and hyperparameters-weights. A drawback is the excessive demand for massive computational power during the training process. Not only as a whole but parts of neural networks can also be in charge of certain functionalities. We present a novel challenge in an intersection between machine learning and variability management communities to reuse modules of DNNs without further training. Let us assume that we are given a DNN for image processing that recognizes cats and dogs. By extracting a part of the network, without additional training a new DNN should be divisible with the functionality of recognizing only cats. Existing research in variability management can offer a foundation for a product line of DNNs composing the reusable functionalities. An ideal solution can be evaluated based on its speed, granularity of determined functionalities, and the support for adding variability to the network. The challenge is decomposed in three subchallenges: feature extraction, feature abstraction, and the implementation of a product line of DNNs.

KW - Deep neural networks

KW - Machine learning

KW - Software product lines

KW - Transfer learning

KW - Variability

UR - http://www.scopus.com/inward/record.url?scp=85123041875&partnerID=8YFLogxK

U2 - 10.1145/3336294.3336321

DO - 10.1145/3336294.3336321

M3 - Conference contribution

AN - SCOPUS:85123041875

T3 - ACM International Conference Proceeding Series (ICPS)

SP - 72

EP - 77

BT - SPLC 2019

A2 - Berger, Thorsten

A2 - Collet, Philippe

A2 - Duchien, Laurence

A2 - Fogdal, Thomas

A2 - Heymans, Patrick

A2 - Kehrer, Timo

A2 - Martinez, Jabier

A2 - Mazo, Raul

A2 - Montalvillo, Leticia

A2 - Salinesi, Camille

A2 - Ternava, Xhevahire

A2 - Thum, Thomas

A2 - Ziadi, Tewfik

PB - Association for Computing Machinery (ACM)

CY - New York

T2 - 23rd International Software Product Line Conference, SPLC 2019

Y2 - 9 September 2019 through 13 September 2019

ER -