Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures

Choosing optimal Deep Learning (DL) architecture and hyperparameters for a particular problem is still not a trivial task among researchers. The most common approach relies on popular architectures proven to work on specific problem domains led on the same experiment environment and setup. However,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gjorgji Noveski, Tome Eftimov, Kostadin Mishev, Monika Simjanoska
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Deep learning intelligent system hyperparameters selection DL architecture selection multi-label classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/a3946492f9bb404e997257a5e51cbebf
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a3946492f9bb404e997257a5e51cbebf
record_format	dspace
spelling	oai:doaj.org-article:a3946492f9bb404e997257a5e51cbebf2021-11-18T00:05:33ZData-Driven Intelligence System for General Recommendations of Deep Learning Architectures2169-353610.1109/ACCESS.2021.3124633https://doaj.org/article/a3946492f9bb404e997257a5e51cbebf2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597522/https://doaj.org/toc/2169-3536Choosing optimal Deep Learning (DL) architecture and hyperparameters for a particular problem is still not a trivial task among researchers. The most common approach relies on popular architectures proven to work on specific problem domains led on the same experiment environment and setup. However, this limits the opportunity to choose or invent novel DL networks that could lead to better results. This paper proposes a novel approach for providing general recommendations of an appropriate DL architecture and its hyperparameters based on different configurations presented in thousands of published research papers that examine various problem domains. This architecture can further serve as a starting point of investigating DL architecture for a concrete data set. Natural language processing (NLP) methods are used to create structured data from unstructured scientific papers upon which intelligent models are learned to propose optimal DL architecture, layer type, and activation functions. The advantage of the proposed methodology is multifold. The first is the ability to eventually use the knowledge and experience from thousands of DL papers published through the years. The second is the contribution to the forthcoming novel researches by aiding the process of choosing optimal DL setup based on the particular problem to be analyzed. The third advantage is the scalability and flexibility of the model, meaning that it can be easily retrained as new papers are published in the future, and therefore to be constantly improved.Gjorgji NoveskiTome EftimovKostadin MishevMonika SimjanoskaIEEEarticleDeep learningintelligent systemhyperparameters selectionDL architecture selectionmulti-label classificationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148710-148720 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning intelligent system hyperparameters selection DL architecture selection multi-label classification Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Deep learning intelligent system hyperparameters selection DL architecture selection multi-label classification Electrical engineering. Electronics. Nuclear engineering TK1-9971 Gjorgji Noveski Tome Eftimov Kostadin Mishev Monika Simjanoska Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures
description	Choosing optimal Deep Learning (DL) architecture and hyperparameters for a particular problem is still not a trivial task among researchers. The most common approach relies on popular architectures proven to work on specific problem domains led on the same experiment environment and setup. However, this limits the opportunity to choose or invent novel DL networks that could lead to better results. This paper proposes a novel approach for providing general recommendations of an appropriate DL architecture and its hyperparameters based on different configurations presented in thousands of published research papers that examine various problem domains. This architecture can further serve as a starting point of investigating DL architecture for a concrete data set. Natural language processing (NLP) methods are used to create structured data from unstructured scientific papers upon which intelligent models are learned to propose optimal DL architecture, layer type, and activation functions. The advantage of the proposed methodology is multifold. The first is the ability to eventually use the knowledge and experience from thousands of DL papers published through the years. The second is the contribution to the forthcoming novel researches by aiding the process of choosing optimal DL setup based on the particular problem to be analyzed. The third advantage is the scalability and flexibility of the model, meaning that it can be easily retrained as new papers are published in the future, and therefore to be constantly improved.
format	article
author	Gjorgji Noveski Tome Eftimov Kostadin Mishev Monika Simjanoska
author_facet	Gjorgji Noveski Tome Eftimov Kostadin Mishev Monika Simjanoska
author_sort	Gjorgji Noveski
title	Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures
title_short	Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures
title_full	Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures
title_fullStr	Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures
title_full_unstemmed	Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures
title_sort	data-driven intelligence system for general recommendations of deep learning architectures
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/a3946492f9bb404e997257a5e51cbebf
work_keys_str_mv	AT gjorgjinoveski datadrivenintelligencesystemforgeneralrecommendationsofdeeplearningarchitectures AT tomeeftimov datadrivenintelligencesystemforgeneralrecommendationsofdeeplearningarchitectures AT kostadinmishev datadrivenintelligencesystemforgeneralrecommendationsofdeeplearningarchitectures AT monikasimjanoska datadrivenintelligencesystemforgeneralrecommendationsofdeeplearningarchitectures
_version_	1718425243129741312

Data-Driven Intelligence System for General Recommendations of Deep Learning Architectures

Ejemplares similares