Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact

Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jan Egger, Antonio Pepe, Christina Gsaxner, Yuan Jin, Jianning Li, Roman Kern
Formato:	article
Lenguaje:	EN
Publicado:	PeerJ Inc. 2021
Materias:	Deep learning Artificial neural networks Machine learning Data analysis Image analysis Language processing Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/12b881bfcd0846b0b3a8a9e6e5d976ba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:12b881bfcd0846b0b3a8a9e6e5d976ba
record_format	dspace
spelling	oai:doaj.org-article:12b881bfcd0846b0b3a8a9e6e5d976ba2021-11-19T15:05:09ZDeep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact10.7717/peerj-cs.7732376-5992https://doaj.org/article/12b881bfcd0846b0b3a8a9e6e5d976ba2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-773.pdfhttps://peerj.com/articles/cs-773/https://doaj.org/toc/2376-5992Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep learning algorithm consists of an artificial neural network, which resembles the biological brain structure. Mimicking the learning process of humans with their senses, deep learning networks are fed with (sensory) data, like texts, images, videos or sounds. These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years. This growth resulted in way over 10,000 publications per year in the last years. For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides already over 11,000 results in Q3 2020 for the search term ‘deep learning’, and around 90% of these results are from the last three years. Consequently, a complete overview over the field of deep learning is already impossible to obtain and, in the near future, it will potentially become difficult to obtain an overview over a subfield. However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks like object detection. With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-survey of selected reviews on deep learning across different scientific disciplines and outline the research impact that they already have during a short period of time. The categories (computer vision, language processing, medical informatics and additional works) have been chosen according to the underlying data sources (image, language, medical, mixed). In addition, we review the common architectures, methods, pros, cons, evaluations, challenges and future directions for every sub-category.Jan EggerAntonio PepeChristina GsaxnerYuan JinJianning LiRoman KernPeerJ Inc.articleDeep learningArtificial neural networksMachine learningData analysisImage analysisLanguage processingElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e773 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Deep learning Artificial neural networks Machine learning Data analysis Image analysis Language processing Electronic computers. Computer science QA75.5-76.95
spellingShingle	Deep learning Artificial neural networks Machine learning Data analysis Image analysis Language processing Electronic computers. Computer science QA75.5-76.95 Jan Egger Antonio Pepe Christina Gsaxner Yuan Jin Jianning Li Roman Kern Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
description	Deep learning belongs to the field of artificial intelligence, where machines perform tasks that typically require some kind of human intelligence. Deep learning tries to achieve this by drawing inspiration from the learning of a human brain. Similar to the basic structure of a brain, which consists of (billions of) neurons and connections between them, a deep learning algorithm consists of an artificial neural network, which resembles the biological brain structure. Mimicking the learning process of humans with their senses, deep learning networks are fed with (sensory) data, like texts, images, videos or sounds. These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years. This growth resulted in way over 10,000 publications per year in the last years. For example, the search engine PubMed alone, which covers only a sub-set of all publications in the medical field, provides already over 11,000 results in Q3 2020 for the search term ‘deep learning’, and around 90% of these results are from the last three years. Consequently, a complete overview over the field of deep learning is already impossible to obtain and, in the near future, it will potentially become difficult to obtain an overview over a subfield. However, there are several review articles about deep learning, which are focused on specific scientific fields or applications, for example deep learning advances in computer vision or in specific tasks like object detection. With these surveys as a foundation, the aim of this contribution is to provide a first high-level, categorized meta-survey of selected reviews on deep learning across different scientific disciplines and outline the research impact that they already have during a short period of time. The categories (computer vision, language processing, medical informatics and additional works) have been chosen according to the underlying data sources (image, language, medical, mixed). In addition, we review the common architectures, methods, pros, cons, evaluations, challenges and future directions for every sub-category.
format	article
author	Jan Egger Antonio Pepe Christina Gsaxner Yuan Jin Jianning Li Roman Kern
author_facet	Jan Egger Antonio Pepe Christina Gsaxner Yuan Jin Jianning Li Roman Kern
author_sort	Jan Egger
title	Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
title_short	Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
title_full	Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
title_fullStr	Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
title_full_unstemmed	Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
title_sort	deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
publisher	PeerJ Inc.
publishDate	2021
url	https://doaj.org/article/12b881bfcd0846b0b3a8a9e6e5d976ba
work_keys_str_mv	AT janegger deeplearningafirstmetasurveyofselectedreviewsacrossscientificdisciplinestheircommonalitieschallengesandresearchimpact AT antoniopepe deeplearningafirstmetasurveyofselectedreviewsacrossscientificdisciplinestheircommonalitieschallengesandresearchimpact AT christinagsaxner deeplearningafirstmetasurveyofselectedreviewsacrossscientificdisciplinestheircommonalitieschallengesandresearchimpact AT yuanjin deeplearningafirstmetasurveyofselectedreviewsacrossscientificdisciplinestheircommonalitieschallengesandresearchimpact AT jianningli deeplearningafirstmetasurveyofselectedreviewsacrossscientificdisciplinestheircommonalitieschallengesandresearchimpact AT romankern deeplearningafirstmetasurveyofselectedreviewsacrossscientificdisciplinestheircommonalitieschallengesandresearchimpact
_version_	1718419996139323392

Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact

Ejemplares similares