Deep Learning

被引：252
作者：
Hao, Xing [1 ]
Zhang, Guigang [1 ,2 ]
Ma, Shang [1 ]
机构：
[1] Univ Calif Irvine, EECS, Irvine, CA 92617 USA
[2] Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
来源：
INTERNATIONAL JOURNAL OF SEMANTIC COMPUTING | 2016年 / 10卷 / 03期
关键词：
Deep learning; neural networks; training;
D O I：
10.1142/S1793351X16500045
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Deep learning is a branch of machine learning that tries to model high-level abstractions of data using multiple layers of neurons consisting of complex structures or non-liner transformations. With the increase of the amount of data and the power of computation, neural networks with more complex structures have attracted widespread attention and been applied to various fields. This paper provides an overview of deep learning in neural networks including popular architecture models and training algorithms.
引用
收藏
页码：417 / 439
页数：23
相关论文
共 57 条
[1]  
Adorf J., 2013, WEB SPEECH API
[2]  
[Anonymous], P ICIMCS AUG
[3]  
Atlas LE, 1988, NEURAL INFORM PROCES, P31
[4]  
Auli M., 2013, P EMNLP, P1044
[5]  
Behnke S, 2003, HIERARCHICAL NEURAL, P2766
[6]  
Bengio Y, 2001, ADV NEUR IN, V13, P932
[7]   Invariant Scattering Convolution Networks [J].
Bruna, Joan ;
Mallat, Stephane .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) :1872-1886
[8]  
Chalasani R., 2013, PROC WORKSHOP INT C, P1
[9]  
Chellapilla Kumar, 2006, 10 INT WORKSH FRONT
[10]  
Cho K., ARXIV1406
123456