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 50 条
  • [31] Real-Valued Backpropagation is Unsuitable for Complex-Valued Neural Networks
    Tan, Zhi-Hao
    Xie, Yi
    Jiang, Yuan
    Zhou, Zhi-Hua
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [32] Image denoising using complex-valued deep CNN
    Quan, Yuhui
    Chen, Yixin
    Shao, Yizhen
    Teng, Huan
    Xu, Yong
    Ji, Hui
    PATTERN RECOGNITION, 2021, 111
  • [33] Representation of complex-valued neural networks: A real-valued approach
    Yadav, A
    Mishra, D
    Ray, S
    Yadav, RN
    Kalra, PK
    2005 International Conference on Intelligent Sensing and Information Processing, Proceedings, 2005, : 331 - 335
  • [34] Complex-Valued End-to-End Deep Network With Coherency Preservation for Complex-Valued SAR Data Reconstruction and Classification
    Asiyabi, Reza Mohammadi
    Datcu, Mihai
    Anghel, Andrei
    Nies, Holger
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [35] Is a Complex-Valued Stepsize Advantageous in Complex-Valued Gradient Learning Algorithms?
    Zhang, Huisheng
    Mandic, Danilo P.
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2016, 27 (12) : 2730 - 2735
  • [36] Complex-Valued Neural Networks With Nonparametric Activation Functions
    Scardapane, Simone
    Van Vaerenbergh, Steven
    Hussain, Amir
    Uncini, Aurelio
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2020, 4 (02): : 140 - 150
  • [37] Conjugate Gradient Algorithms for Complex-Valued Neural Networks
    Popa, Calin-Adrian
    NEURAL INFORMATION PROCESSING, PT II, 2015, 9490 : 412 - 422
  • [38] Proposal of fully augmented complex-valued neural networks
    Nitta, Tohru
    IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2023, 14 (02): : 175 - 192
  • [39] Prediction of Complex-Valued Signals by Using Complex-Valued LMK Algorithm
    Menguc, Engin Cemal
    Acir, Nurettin
    2017 25TH SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2017,
  • [40] Complex-Valued Radio Signal Loss for Neural Networks
    Logue, Kyle
    2023 IEEE AEROSPACE CONFERENCE, 2023,
12345