Fourier series neural networks for regression

机译：傅里叶级数神经网络回归

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

An innovative efficient and fast neural networks in which hidden neurons are constructed based on Fourier series expansions (FSNN), half-range cosine (FCSNN) and sine expansions (FSSNN) are proposed and tested for linear and nonlinear regulation problems. The results of numerical examples using FSNN are compared with those obtained from traditional linear regression (LP), nonlinear regression (NLP), backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). The results obtained from FSNN agree well with those obtained from LP, NLP, BPANN and RBFNN and show global approximation features to the fitting data. Only a few hidden neurons are required to obtain very good and fast convergence of regression as compared with BPANN and RBFNN.

机译：提出了一种创新的高效快速神经网络，其中基于傅立叶级数展开（FSNN），半距余弦（FCSNN）和正弦展开（FSSNN）构造隐藏神经元，并针对线性和非线性调节问题进行了测试。将使用FSNN的数值示例的结果与从传统线性回归（LP），非线性回归（NLP），向后传播神经网络（BPANN）和径向基函数神经网络（RBFNN）获得的结果进行比较。从FSNN获得的结果与从LP，NLP，BPANN和RBFNN获得的结果非常吻合，并显示了拟合数据的全局近似特征。与BPANN和RBFNN相比，只需很少的隐藏神经元即可获得非常好的快速收敛。

著录项

来源
《Proceedings of 4th IEEE International Conference on Applied System Invention》|2018年|716-719|共4页
会议地点 Chiba(JP)
作者
Yung-Ming Wang; Li-Jeng Huang;
展开▼
作者单位

Department of Civil Engineering, National Cheng-Kung University, No. 1, University Road, Tainan, Taiwan, R.O.C.;

Department of Civil Engineering, National Kaohsiung University of Science and Technology, No. 415, Chieng Kung Rd., Sanmin District, Kaohsiung, Taiwan. R.O.C.;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类
关键词
Neurons; Fourier series; Biological neural networks; Linear regression; Training; Topology; Artificial neural networks;

机译：神经元;傅立叶级数;生物神经网络;线性回归;训练;拓扑;人工神经网络;;

相似文献

外文文献
中文文献
专利

1. On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks [J] . Wang Sifan, Wang Hanwen, Perdikaris Paris Computer Methods in Applied Mechanics and Engineering . 2021,第Octa1期

机译：在傅立叶特征网络的特征向量偏见：从回归解决与物理信息的神经网络的多尺度PDE
2. Predicting blood p-hydroxybutyrate using milk Fourier transform infrared spectrum, milk composition, and producer-reported variables with multiple linear regression, partial least squares regression, and artificial neural network [J] . R.S. Pralle, K.W. Weigel, H.M. White Journal of dairy science . 2018,第5期

机译：使用牛奶线性傅立叶变换红外光谱，牛奶成分和生产者报告的变量进行多元线性回归，偏最小二乘回归和人工神经网络预测血液对羟基丁酸酯
3. DETERMINING THE WEIGHTS OF A FOURIER SERIES NEURAL NETWORK ON THE BASIS OF THE MULTIDIMENSIONAL DISCRETE FOURIER TRANSFORM [J] . Krzysztof Halawa International Journal of Applied Mathematics and Computer Science . 2008,第3期

机译：基于多维离散傅里叶变换的傅里叶神经网络权重的确定
4. Fourier series neural networks for regression [C] . Yung-Ming Wang, Li-Jeng Huang International Conference on Applied System Innovation . 2018

机译：傅里叶系列的回归神经网络
5. Stochastic neural networks and their applications to regression analysis and time series forecasting. [D] . Wong, Samuel Po-Shing. 1997

机译：随机神经网络及其在回归分析和时间序列预测中的应用。
6. Comparison of autoregressive integrated moving average model and generalised regression neural network model for prediction of haemorrhagic fever with renal syndrome in China: a time-series study [O] . Ya-wen Wang, Zhong-zhou Shen, Yu Jiang 2019

机译：自回归综合移动平均模型与广义回归神经网络模型在中国肾综合征出血热预测中的比较：时间序列研究
7. DETERMINING THE WEIGHTS OF A FOURIER SERIES NEURAL NETWORK ON THE BASIS OF THE MULTIDIMENSIONAL DISCRETE FOURIER TRANSFORM [O] . Krzysztof Halawa 2013

机译：基于多维离散傅立叶变换确定傅立叶级神经网络的权重

Fourier series neural networks for regression

摘要

著录项

相似文献

相关主题

期刊订阅