详细信息
文献类型:期刊文献
中文题名:The construction and approximation of some neural networks operators
英文题名:The construction and approximation of some neural networks operators
作者:Chen Zhi-xiang[2];Cao Fei-long[1];Zhao Jian-wei[1]
机构:[1]China Jiliang Univ, Dept Math, Hangzhou 310018, Zhejiang, Peoples R China;[2]Shaoxing Univ, Dept Math, Shaoxing 312000, Peoples R China
年份:2012
卷号:27
期号:1
起止页码:69
中文期刊名:高校应用数学学报:英文版(B辑)
外文期刊名:APPLIED MATHEMATICS-A JOURNAL OF CHINESE UNIVERSITIES SERIES B
收录:SCI-EXPANDED(收录号:WOS:000301606000006)、、Scopus(收录号:2-s2.0-84863375184)、CSCD2011_2012、WOS、CSCD
基金:Supported by the National Natural Science Foundation of China (61179041, 61101240) and the Zhejiang Provincial Natural Science Foundation of China (Y6110117).
语种:英文
中文关键词:网络运营商;级数逼近;神经;Riesz平均;度量函数;时间间隔;连续函数;二元函数
外文关键词:approximation; sigmoidal function; neural network operator; Bochner-Riesz mean
中文摘要:In this paper, the technique of approximate partition of unity is used to construct a class of neural networks operators with sigmoidal functions. Using the modulus of continuity of function as a metric, the errors of the operators approximating continuous functions defined on a compact interval are estimated. Furthmore, Bochner-Riesz means operators of double Fourier series are used to construct networks operators for approximating bivariate functions, and the errors of approximation by the operators are estimated.
外文摘要:In this paper, the technique of approximate partition of unity is used to construct a class of neural networks operators with sigmoidal functions. Using the modulus of continuity of function as a metric, the errors of the operators approximating continuous functions defined on a compact interval are estimated. Furthmore, Bochner-Riesz means operators of double Fourier series are used to construct networks operators for approximating bivariate functions, and the errors of approximation by the operators are estimated.
参考文献:
正在载入数据...