A Review of Deep Machine Learning

被引：45
作者：
Benuwa, Ben-Bright [1 ,2 ]
Zhan, Yongzhao [1 ]
Ghansah, Benjamin [1 ,2 ]
Wornyo, Dickson Keddy [1 ]
Kataka, Frank Banaseka [1 ]
机构：
[1] Jiangsu Univ, Sch Comp Sci & Telecommun Engn, Xuefu Rd 301, Jiangsu City 212013, Zhenjiang, Peoples R China
[2] Data Link Inst, Sch Comp Sci, POB 2481, Tema Ghana, West Africa, Ghana
来源：
INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH IN AFRICA | 2016年 / 24卷
关键词：
Deep learning; Deep belief networks; feature learning; unsupervised learning; Boltzmann Machine; neural nets;
D O I：
10.4028/www.scientific.net/JERA.24.124
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
The rapid increase of information and accessibility in recent years has activated a paradigm shift in algorithm design for artificial intelligence. Recently, Deep Learning (a surrogate of Machine Learning) have won several contests in pattern recognition and machine learning. This review comprehensively summarises relevant studies, much of it from prior state-of-the-art techniques. This paper also discusses the motivations and principles regarding learning algorithms for deep architectures.
引用
收藏
页码：124 / 136
页数：13
相关论文
共 67 条
[31]  
Islam MM, 2008, STUD COMPUT INTELL, V115, P851
[32]  
Kavukcuoglu K, 2009, PROC CVPR IEEE, P1605, DOI 10.1109/CVPRW.2009.5206545
[33]  
Khorshed T., RES PROBLEM DEFINITI
[34]  
Kombrink S, 2011, 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, P2888
[35]   Deep Neural Networks: A New Framework for Modeling Biological Vision and Brain Information Processing [J].
Kriegeskorte, Nikolaus .
ANNUAL REVIEW OF VISION SCIENCE, VOL 1, 2015, 1 :417-446
[36]  
Krizhevsky A., 2010, CONVOLUTIONAL UNPUB, P1
[37]  
Krizhevsky A., 2012, ADV NEURAL INFORM PR, P1097
[38]  
Kwolek B, 2005, LECT NOTES COMPUT SC, V3696, P551, DOI 10.1007/11550822_86
[39]  
Larochelle H., 2007, ICML, V227, P473, DOI DOI 10.1145/1273496.1273556
[40]   Gradient-based learning applied to document recognition [J].
Lecun, Y ;
Bottou, L ;
Bengio, Y ;
Haffner, P .
PROCEEDINGS OF THE IEEE, 1998, 86 (11) :2278-2324
1234567