Repository for reusing artifacts of artificial neural networks
Repository for reusing artifacts of artificial neural networks
Artificial Neural Networks (ANNs) replaced conventional software systems in various domains such as machine translation, natural language processing, and image processing. So, why do we need a repository for artificial neural networks? Those systems are developed with labeled data and we have strong dependencies between the data that is used for training and testing our network. Another challenge is the data quality as well as reuse-ability. There we are trying to apply concepts from classic software engineering that is not limited to the model, while data and code haven't been dealt with mostly in other projects. The first question that comes to mind might be, why don't we use GitHub, a well known widely spread tool for reuse, for our issue. And the reason why is that GitHub, although very good in its class is not developed for machine learning appliances and focuses more on software reuse. In addition to that GitHub does not allow to execute the code directly on the platform which would be very convenient for collaborative work on one project.
cs.LG, cs.SE
Ghofrani, Javad
533baa0d-11b8-464f-8023-a686bea1e431
Kozegar, Ehsan
1c29773e-2787-425c-84e0-1a70cb520bd9
Soorati, Mohammad Divband
35fe6bbb-ce52-4c21-a46e-9bb0e31d246c
Bozorgmehr, Arezoo
8b78430c-782f-4d37-afcc-2f21eb88341f
Chen, Hongfei
66440054-1e5c-41d8-967d-e96f457b1b43
Naake, Maximilian
64a4496a-edd7-4065-993b-26bcf5e037a3
30 March 2020
Ghofrani, Javad
533baa0d-11b8-464f-8023-a686bea1e431
Kozegar, Ehsan
1c29773e-2787-425c-84e0-1a70cb520bd9
Soorati, Mohammad Divband
35fe6bbb-ce52-4c21-a46e-9bb0e31d246c
Bozorgmehr, Arezoo
8b78430c-782f-4d37-afcc-2f21eb88341f
Chen, Hongfei
66440054-1e5c-41d8-967d-e96f457b1b43
Naake, Maximilian
64a4496a-edd7-4065-993b-26bcf5e037a3
[Unknown type: UNSPECIFIED]
Abstract
Artificial Neural Networks (ANNs) replaced conventional software systems in various domains such as machine translation, natural language processing, and image processing. So, why do we need a repository for artificial neural networks? Those systems are developed with labeled data and we have strong dependencies between the data that is used for training and testing our network. Another challenge is the data quality as well as reuse-ability. There we are trying to apply concepts from classic software engineering that is not limited to the model, while data and code haven't been dealt with mostly in other projects. The first question that comes to mind might be, why don't we use GitHub, a well known widely spread tool for reuse, for our issue. And the reason why is that GitHub, although very good in its class is not developed for machine learning appliances and focuses more on software reuse. In addition to that GitHub does not allow to execute the code directly on the platform which would be very convenient for collaborative work on one project.
More information
Published date: 30 March 2020
Additional Information:
tool paper https://github.com/ghofrani85/RAN2 7 pages
Keywords:
cs.LG, cs.SE
Identifiers
Local EPrints ID: 473319
URI: http://eprints.soton.ac.uk/id/eprint/473319
PURE UUID: 090671cb-cc64-419b-b5b7-06d2daae5b5b
Catalogue record
Date deposited: 13 Jan 2023 18:06
Last modified: 17 Mar 2024 03:57
Export record
Altmetrics
Contributors
Author:
Javad Ghofrani
Author:
Ehsan Kozegar
Author:
Mohammad Divband Soorati
Author:
Arezoo Bozorgmehr
Author:
Hongfei Chen
Author:
Maximilian Naake
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