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

页码：526 / +

页数：2

共 50 条

[31] Complex-valued GMDH-type neural network for real-valued classification problems
Xiao, Jin
Hu, Yi
Wang, Shouyang
2013 SIXTH INTERNATIONAL CONFERENCE ON BUSINESS INTELLIGENCE AND FINANCIAL ENGINEERING (BIFE), 2014, : 70 - 74
[32] BinVPR: Binary Neural Networks towards Real-Valued for Visual Place Recognition
Wang, Junshuai
Han, Junyu
Dong, Ruifang
Kan, Jiangming
SENSORS, 2024, 24 (13)
[33] Application of neural networks incorporated with real-valued genetic algorithms in knowledge acquisition
Su, MC
Chang, HT
FUZZY SETS AND SYSTEMS, 2000, 112 (01) : 85 - 97
[34] Application of stochastic real-valued reinforcement neural networks to batch production rescheduling
Heywood, MI
Chan, MC
Chatwin, CR
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART B-JOURNAL OF ENGINEERING MANUFACTURE, 1997, 211 (08) : 591 - 603
[35] COMPLEX-VALUED ROOTS OF REAL-VALUED CHARACTERISTIC FUNCTIONS
STAUDTE, RG
TATA, MN
NOTICES OF THE AMERICAN MATHEMATICAL SOCIETY, 1970, 17 (01): : 123 - &
[36] Vapnik-Chervonenkis generalization bounds for real valued neural networks
Hole, A
NEURAL COMPUTATION, 1996, 8 (06) : 1277 - 1299
[37] Circular Complex-Valued GMDH-Type Neural Network for Real-Valued Classification Problems
Xiao, Jin
Jia, Yanlin
Jiang, Xiaoyi
Wang, Shouyang
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (12) : 5285 - 5299
[38] COMPLEX-VALUED VS. REAL-VALUED CONVOLUTIONAL NEURAL NETWORK FOR POLSAR DATA CLASSIFICATION
Asiyabi, Reza Mohammadi
Datcu, Mihai
Nies, Holger
Anghel, Andrei
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 421 - 424
[39] An Efficient Hybrid Incremental Algorithm for Complex-Valued Feedforward Neural Networks
Zhang, Shufang
Huang, He
Han, Ziyang
2019 9TH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY (ICIST2019), 2019, : 327 - 332
[40] Bayesian model comparison versus generalization ability of neural networks
Gomari, M
Järvi, T
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL I AND II, 1999, : 537 - 541

← 1 2 3 4 5 →