DocumentCode
1356010
Title
Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier]
Author
Arel, Itamar ; Rose, Derek C. ; Karnowski, T.P.
Author_Institution
Univ. of Tennessee, Knoxville, TN, USA
Volume
5
Issue
4
fYear
2010
Firstpage
13
Lastpage
18
Abstract
This article provides an overview of the mainstream deep learning approaches and research directions proposed over the past decade. It is important to emphasize that each approach has strengths and "weaknesses, depending on the application and context in "which it is being used. Thus, this article presents a summary on the current state of the deep machine learning field and some perspective into how it may evolve. Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs) (and their respective variations) are focused on primarily because they are well established in the deep learning field and show great promise for future work.
Keywords
belief networks; learning (artificial intelligence); neural nets; CNN; DBN; artificial intelligence research; convolutional neural networks; deep belief networks; deep machine learning approach;
fLanguage
English
Journal_Title
Computational Intelligence Magazine, IEEE
Publisher
ieee
ISSN
1556-603X
Type
jour
DOI
10.1109/MCI.2010.938364
Filename
5605630
Link To Document