The University of Southampton
University of Southampton Institutional Repository

DeepSaucer: Unified environment for verifying Deep Neural Networks

DeepSaucer: Unified environment for verifying Deep Neural Networks
DeepSaucer: Unified environment for verifying Deep Neural Networks
In recent years, a number of methods for verifying DNNs have been developed. Because the approaches of the methods differ and have their own limitations, we think that a number of verification methods should be applied to a developed DNN. To apply a number of methods to the DNN, it is necessary to translate either the implementation of the DNN or the verification method so that one runs in the same environment as the other. Since those translations are time-consuming, a utility tool, named DeepSaucer, which helps to retain and reuse implementations of DNNs, verification methods, and their environments, is proposed. In DeepSaucer, code snippets of loading DNNs, running verification methods, and creating their environments are retained and reused as software assets in order to reduce cost of verifying DNNs. The feasibility of DeepSaucer is confirmed by implementing it on the basis of Anaconda, which provides virtual environment for loading a DNN and running a verification method. In addition, the effectiveness of DeepSaucer is demonstrated by usecase examples.
cs.SE, cs.LG
Sato, Naoto
3fc2809c-6041-4c12-897e-a1aa20ab6ac8
Kuruma, Hironobu
3f105559-e14c-4f32-9277-05dae50438d3
Kaneko, Masanori
20a22712-1daa-48ef-9993-c7e05729a846
Nakagawa, Yuichiroh
74face77-fdcc-4f69-ab70-1e0f655ba282
Ogawa, Hideto
ecd9a161-8657-49ea-b5fc-5c7de1efae2c
Hoang, Thai Son
dcc0431d-2847-4e1d-9a85-54e4d6bab43f
Butler, Michael
54b9c2c7-2574-438e-9a36-6842a3d53ed0
Sato, Naoto
3fc2809c-6041-4c12-897e-a1aa20ab6ac8
Kuruma, Hironobu
3f105559-e14c-4f32-9277-05dae50438d3
Kaneko, Masanori
20a22712-1daa-48ef-9993-c7e05729a846
Nakagawa, Yuichiroh
74face77-fdcc-4f69-ab70-1e0f655ba282
Ogawa, Hideto
ecd9a161-8657-49ea-b5fc-5c7de1efae2c
Hoang, Thai Son
dcc0431d-2847-4e1d-9a85-54e4d6bab43f
Butler, Michael
54b9c2c7-2574-438e-9a36-6842a3d53ed0

Sato, Naoto, Kuruma, Hironobu, Kaneko, Masanori, Nakagawa, Yuichiroh, Ogawa, Hideto, Hoang, Thai Son and Butler, Michael (2018) DeepSaucer: Unified environment for verifying Deep Neural Networks. arXiv.

Record type: Article

Abstract

In recent years, a number of methods for verifying DNNs have been developed. Because the approaches of the methods differ and have their own limitations, we think that a number of verification methods should be applied to a developed DNN. To apply a number of methods to the DNN, it is necessary to translate either the implementation of the DNN or the verification method so that one runs in the same environment as the other. Since those translations are time-consuming, a utility tool, named DeepSaucer, which helps to retain and reuse implementations of DNNs, verification methods, and their environments, is proposed. In DeepSaucer, code snippets of loading DNNs, running verification methods, and creating their environments are retained and reused as software assets in order to reduce cost of verifying DNNs. The feasibility of DeepSaucer is confirmed by implementing it on the basis of Anaconda, which provides virtual environment for loading a DNN and running a verification method. In addition, the effectiveness of DeepSaucer is demonstrated by usecase examples.

Full text not available from this repository.

More information

Published date: 9 November 2018
Keywords: cs.SE, cs.LG

Identifiers

Local EPrints ID: 429257
URI: https://eprints.soton.ac.uk/id/eprint/429257
PURE UUID: cec2a515-0644-466e-bb4b-e6744692d5c4
ORCID for Thai Son Hoang: ORCID iD orcid.org/0000-0003-4095-0732
ORCID for Michael Butler: ORCID iD orcid.org/0000-0003-4642-5373

Catalogue record

Date deposited: 25 Mar 2019 17:30
Last modified: 26 Mar 2019 01:36

Export record

Contributors

Author: Naoto Sato
Author: Hironobu Kuruma
Author: Masanori Kaneko
Author: Yuichiroh Nakagawa
Author: Hideto Ogawa
Author: Thai Son Hoang ORCID iD
Author: Michael Butler ORCID iD

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×