Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact
Open Access
- 17 November 2021
- journal article
- research article
- Published by PeerJ in PeerJ Computer Science
- Vol. 7, e773
Abstract
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.Keywords
All Related Versions
Funding Information
- Austrian Science Fund (KLI 678-B31)
- TU Graz LEAD project
- CAMed (871132)
- Austrian Federal Ministry of Transport, Innovation and Technology
- Austrian Federal Ministry for Digital and Economic Affairs
- Styrian Business Promotion Agency
This publication has 71 references indexed in Scilit:
- Going deeper into action recognition: A surveyImage and Vision Computing, 2017
- Deep Learning for Health InformaticsIEEE Journal of Biomedical and Health Informatics, 2016
- The Evolution of Computing: AlphaGoComputing in Science & Engineering, 2016
- Deep learning for visual understanding: A reviewNeurocomputing, 2016
- Deep learningNature, 2015
- Deep Learning: Methods and ApplicationsFoundations and Trends® in Signal Processing, 2014
- Deep BlueArtificial Intelligence, 2002
- Comparing images using the Hausdorff distanceIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- A logical calculus of the ideas immanent in nervous activity. 1943.1990
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1990