Cargando…

A review of some techniques for inclusion of domain-knowledge into deep neural networks

We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using hum...

Descripción completa

Detalles Bibliográficos
Autores principales: Dash, Tirtharaj, Chitlangia, Sharad, Ahuja, Aditya, Srinivasan, Ashwin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8776800/
https://www.ncbi.nlm.nih.gov/pubmed/35058487
http://dx.doi.org/10.1038/s41598-021-04590-0
_version_ 1784636916281376768
author Dash, Tirtharaj
Chitlangia, Sharad
Ahuja, Aditya
Srinivasan, Ashwin
author_facet Dash, Tirtharaj
Chitlangia, Sharad
Ahuja, Aditya
Srinivasan, Ashwin
author_sort Dash, Tirtharaj
collection PubMed
description We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines the inclusion of domain-knowledge by means of changes to: the input, the loss-function, and the architecture of deep networks. The categorisation is for ease of exposition: in practice we expect a combination of such changes will be employed. In each category, we describe techniques that have been shown to yield significant changes in the performance of deep neural networks.
format Online
Article
Text
id pubmed-8776800
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group UK
record_format MEDLINE/PubMed
spelling pubmed-87768002022-01-24 A review of some techniques for inclusion of domain-knowledge into deep neural networks Dash, Tirtharaj Chitlangia, Sharad Ahuja, Aditya Srinivasan, Ashwin Sci Rep Article We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines the inclusion of domain-knowledge by means of changes to: the input, the loss-function, and the architecture of deep networks. The categorisation is for ease of exposition: in practice we expect a combination of such changes will be employed. In each category, we describe techniques that have been shown to yield significant changes in the performance of deep neural networks. Nature Publishing Group UK 2022-01-20 /pmc/articles/PMC8776800/ /pubmed/35058487 http://dx.doi.org/10.1038/s41598-021-04590-0 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Dash, Tirtharaj
Chitlangia, Sharad
Ahuja, Aditya
Srinivasan, Ashwin
A review of some techniques for inclusion of domain-knowledge into deep neural networks
title A review of some techniques for inclusion of domain-knowledge into deep neural networks
title_full A review of some techniques for inclusion of domain-knowledge into deep neural networks
title_fullStr A review of some techniques for inclusion of domain-knowledge into deep neural networks
title_full_unstemmed A review of some techniques for inclusion of domain-knowledge into deep neural networks
title_short A review of some techniques for inclusion of domain-knowledge into deep neural networks
title_sort review of some techniques for inclusion of domain-knowledge into deep neural networks
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8776800/
https://www.ncbi.nlm.nih.gov/pubmed/35058487
http://dx.doi.org/10.1038/s41598-021-04590-0
work_keys_str_mv AT dashtirtharaj areviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT chitlangiasharad areviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT ahujaaditya areviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT srinivasanashwin areviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT dashtirtharaj reviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT chitlangiasharad reviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT ahujaaditya reviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks
AT srinivasanashwin reviewofsometechniquesforinclusionofdomainknowledgeintodeepneuralnetworks