Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Automated Search for Configurations of Deep Neural Network Architectures
Ghamizi, Salah; Cordy, Maxime; Papadakis, Mike et al.
2019In Automated Search for Configurations of Convolutional Neural Network Architectures
Peer reviewed
 

Files


Full Text
SPLC19___Configuration_of_Deep_Neural_Networks.pdf
Author preprint (1.14 MB)
:qin Pqper
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
neural networks; feature model; configuration search
Abstract :
[en] Deep Neural Networks (DNNs) are intensively used to solve a wide variety of complex problems. Although powerful, such systems require manual configuration and tuning. To this end, we view DNNs as configurable systems and propose an end-to-end framework that allows the configuration, evaluation and automated search for DNN architectures. Therefore, our contribution is threefold. First, we model the variability of DNN architectures with a Feature Model (FM) that generalizes over existing architectures. Each valid configuration of the FM corresponds to a valid DNN model that can be built and trained. Second, we implement, on top of Tensorflow, an automated procedure to deploy, train and evaluate the performance of a configured model. Third, we propose a method to search for configurations and demonstrate that it leads to good DNN models. We evaluate our method by applying it on image classification tasks (MNIST, CIFAR-10) and show that, with limited amount of computation and training, our method can identify high-performing architectures (with high accuracy). We also demonstrate that we outperform existing state-of-the-art architectures handcrafted by ML researchers. Our FM and framework have been released to support replication and future research.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > Security Design and Validation Research Group (SerVal)
Disciplines :
Computer science
Author, co-author :
Ghamizi, Salah ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Computer Science and Communications Research Unit (CSC)
Cordy, Maxime  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Papadakis, Mike ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > Computer Science and Communications Research Unit (CSC)
Le Traon, Yves ;  University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)
External co-authors :
no
Language :
English
Title :
Automated Search for Configurations of Deep Neural Network Architectures
Publication date :
2019
Event name :
SPLC '19: 23rd International Systems and Software Product Line Conference
Event date :
Sept 09-13, 2019
Audience :
International
Main work title :
Automated Search for Configurations of Convolutional Neural Network Architectures
Collection name :
Volume A Pages 119–130
Peer reviewed :
Peer reviewed
Focus Area :
Computational Sciences
FnR Project :
FNR11686509 - Continuous Development With Mutation Analysis And Testing, 2017 (01/09/2018-31/08/2021) - Michail Papadakis
Name of the research project :
CODEMATES
Funders :
FNR - Fonds National de la Recherche [LU]
Available on ORBilu :
since 09 April 2019

Statistics


Number of views
205 (38 by Unilu)
Number of downloads
101 (19 by Unilu)

Scopus citations®
 
8
Scopus citations®
without self-citations
5
OpenCitations
 
4
WoS citations
 
4

Bibliography


Similar publications



Contact ORBilu