Comparison of Complex- and Real-Valued Feedforward Neural Networks in Their Generalization Ability

被引：0
|
作者：
Hirose, Akira [1 ]
Yoshida, Shotaro [1 ]
机构：
[1] Univ Tokyo, Dept Elect Engn & Informat Syst, Tokyo 1138654, Japan
来源：
NEURAL INFORMATION PROCESSING, PT I | 2011年 / 7062卷
关键词：
Complex-valued neural network; function approximation; generalization; BACKPROPAGATION ALGORITHM;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We compare the generalization characteristics of complex-valued and real-valued feedforward neural networks when they deal with wave-related signals. We assume a task of function approximation. Experiments demonstrate that complex-valued neural networks show smaller generalization error than real-valued ones in particular when the signals have high degree of wave nature.
引用
收藏
页码：526 / +
页数：2
相关论文
共 50 条
  • [21] Real-Valued Neural Networks for Complex-Valued Impairment Compensation Using Digital Up-Conversion
    Paryanti, Gil
    Sadot, Dan
    IEEE TRANSACTIONS ON COMMUNICATIONS, 2020, 68 (12) : 7511 - 7520
  • [22] Guest Editorial Special Issue on Complex- and Hypercomplex-Valued Neural Networks
    Hirose, Akira
    Aizenberg, Igor
    Mandic, Danilo P.
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (09) : 1597 - 1599
  • [23] Comparison between real and complex valued neural networks in communication applications
    Benvenuto, N.
    Marchesi, M.
    Piazza, F.
    Uncini, A.
    Proceedings of the International Conference on Artificial Neural Networks, 1991,
  • [24] ABOUT THE EQUIVALENCE BETWEEN COMPLEX-VALUED AND REAL-VALUED FULLY CONNECTED NEURAL NETWORKS - APPLICATION TO POLINSAR IMAGES
    Barrachina, J. A.
    Ren, C.
    Vieillard, G.
    Morisseau, C.
    Ovarlez, J-P
    2021 IEEE 31ST INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2021,
  • [25] A Fast Learning Complex-valued Neural Classifier for Real-valued Classification Problems
    Savitha, R.
    Suresh, S.
    Sundararajan, N.
    2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 2243 - 2249
  • [26] Representations and rates of approximation of real-valued Boolean functions by neural networks
    Kurkova, V
    Savicky, P
    Hlavackova, K
    NEURAL NETWORKS, 1998, 11 (04) : 651 - 659
  • [27] COMPLEX-VALUED VS. REAL-VALUED NEURAL NETWORKS FOR CLASSIFICATION PERSPECTIVES: AN EXAMPLE ON NON-CIRCULAR DATA
    Barrachina, J. A.
    Ren, C.
    Morisseau, C.
    Vieillard, G.
    Ovarlez, J-P
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 2990 - 2994
  • [28] Complex-Valued Feedforward Neural Networks Learning Without Backpropagation
    Guo, Wei
    Huang, He
    Huang, Tingwen
    NEURAL INFORMATION PROCESSING (ICONIP 2017), PT IV, 2017, 10637 : 100 - 107
  • [29] Fully coupled and feedforward neural networks with complex-valued neurons
    Zurada, Jacek M.
    Aizenberg, Igor
    ADVANCES IN INTELLIGENT AND DISTRIBUTED COMPUTING, 2008, 78 : 41 - +
  • [30] Single-layered complex-valued neural network for real-valued classification problems
    Amin, Md. Faijul
    Murase, Kazuyuki
    NEUROCOMPUTING, 2009, 72 (4-6) : 945 - 955
12345