Complex-Valued Deep Belief Networks

被引:9
作者
Popa, Calin-Adrian [1 ]
机构
[1] Polytech Univ Timisoara, Dept Comp & Software Engn, Blvd V Parvan 2, Timisoara 300223, Romania
来源
ADVANCES IN NEURAL NETWORKS - ISNN 2018 | 2018年 / 10878卷
关键词
Complex-valued neural networks; Deep belief networks; Deep neural networks;
D O I
10.1007/978-3-319-92537-0_9
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Deep belief networks were among the first models in the deep learning paradigm. Their use for unsupervised pretraining allowed deep neural network architectures to perform better than shallow ones. This paper introduces complex-valued deep belief networks, which can be used for unsupervised pretraining of complex-valued deep neural networks. Experiments on the MNIST dataset using different network architectures show better results of the complex-valued networks compared to their real-valued counterparts, when complex-valued deep belief networks are used for pretraining them.
引用
收藏
页码:72 / 78
页数:7
相关论文
共 16 条
[1]  
Arjovsky M., 2016, ICML 2016
[2]  
Bengio Y., 2006, ADV NEURAL INFORM PR, V19
[3]   Learning Deep Architectures for AI [J].
Bengio, Yoshua .
FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 2 (01) :1-127
[4]   Invariant Scattering Convolution Networks [J].
Bruna, Joan ;
Mallat, Stephane .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (08) :1872-1886
[5]  
Erhan D, 2010, J MACH LEARN RES, V11, P625
[6]  
Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
[7]   A fast learning algorithm for deep belief nets [J].
Hinton, Geoffrey E. ;
Osindero, Simon ;
Teh, Yee-Whye .
NEURAL COMPUTATION, 2006, 18 (07) :1527-1554
[8]  
Jing L., 2017, ICML 2017
[9]   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
[10]   Deep learning [J].
LeCun, Yann ;
Bengio, Yoshua ;
Hinton, Geoffrey .
NATURE, 2015, 521 (7553) :436-444