Back to Search
Start Over
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
- Source :
- Journal of Big Data, Vol 8, Iss 1, Pp 1-74 (2021), Journal of Big Data
- Publication Year :
- 2021
- Publisher :
- SpringerOpen, 2021.
-
Abstract
- In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.
- Subjects :
- Information Systems and Management
lcsh:Computer engineering. Computer hardware
Computer Networks and Communications
Computer science
Image classification
Survey Paper
GPU
lcsh:TK7885-7895
02 engineering and technology
Machine learning
computer.software_genre
Convolutional neural network
Field (computer science)
lcsh:QA75.5-76.95
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Medical image analysis
Deep learning applications
0202 electrical engineering, electronic engineering, information engineering
FPGA
Point (typography)
lcsh:T58.5-58.64
business.industry
lcsh:Information technology
Deep learning
Supervised learning
Robotics
Transfer learning
Hardware and Architecture
Convolution neural network (CNN)
Benchmark (computing)
020201 artificial intelligence & image processing
Deep neural network architectures
Artificial intelligence
lcsh:Electronic computers. Computer science
Transfer of learning
business
computer
Information Systems
Subjects
Details
- Language :
- English
- ISSN :
- 21961115
- Volume :
- 8
- Issue :
- 1
- Database :
- OpenAIRE
- Journal :
- Journal of Big Data
- Accession number :
- edsair.doi.dedup.....7498d3a16e822843a53a41e10519b1e6