Reference : Automated Search for Configurations of Deep Neural Network Architectures

	Document type :	Scientific congresses, symposiums and conference proceedings : Unpublished conference
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Computational Sciences
	To cite this reference:	http://hdl.handle.net/10993/39320

Title :	Automated Search for Configurations of Deep Neural Network Architectures
Language :	English
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) >]
Publication date :	2019
Peer reviewed :	Yes
Event name :	SPLC '19: 23rd International Systems and Software Product Line Conference
Event date :	Sept 09-13, 2019
Keywords :	[en] 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.
Target :	Researchers ; Professionals
Permalink :	http://hdl.handle.net/10993/39320

	File(s) associated to this reference
	Fulltext file(s): File Commentary Version Size Access Open access SPLC19___Configuration_of_Deep_Neural_Networks.pdf :qin Pqper Author preprint 1.12 MB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map