A comprehensive review of deep learning algorithms
Varastehpour, Soheil; Sharifzadeh, Hamid; Ardekani, Iman
View fulltext online
Citation:Varastehpour, S., Sharifzadeh, H., Ardekani, I. (2021). A Comprehensive Review of Deep Learning Algorithms. (Unitec ePress Occasional and Discussion Paper Series 2021/4). Unitec ePress . ISSN 2324-3635. http://www.unitec.ac.nz/epress.
Permanent link to Research Bank record:https://hdl.handle.net/10652/5421
Deep learning algorithms are a subset of machine learning algorithms that aim to explore several levels of the distributed representations from the input data. Recently, many deep learning algorithms have been proposed to solve traditional artificial intelligence problems. In this review paper, some of the up-to-date algorithms of this topic in the field of computer vision and image processing are reviewed. Following this, a brief overview of several different deep learning methods and their recent developments are discussed
Keywords:artificial intelligence (AI), deep-learning algorithms, Convolutional Neural Network (CNN), autoencoders, restricted Boltzmann machine, sparse coding, literature reviews
ANZSRC Field of Research:080108 Neural, Evolutionary and Fuzzy Computation, 080109 Pattern Recognition and Data Mining
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-NoDerivatives 4.0 International
Copyright Notice:A Comprehensive Review of Deep Learning Algorithms by Dr Soheil Varastehpour, Dr Hamid Sharifzadeh and Dr Iman Ardekani is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Rights:This digital work is protected by copyright. It may be consulted by you, provided you comply with the provisions of the Act and the following conditions of use. These documents or images may be used for research or private study purposes. Whether they can be used for any other purpose depends upon the Copyright Notice above. You will recognise the author's and publishers rights and give due acknowledgement where appropriate.
MetadataShow detailed record
This item appears in
The following license files are associated with this item: