Constructive Approximation by Superposition of Sigmoidal Functions

作者: Danilo Costarelli , Renato Spigler

DOI: 10.4208/ATA.2013.V29.N2.8

关键词:

摘要: In this paper, a constructive theory is developed for approximating func- tions of one or more variables by superposition sigmoidal functions. This done in the uniform norm as well L p norm. Results simultaneous approx- imation, with same order accuracy, function and its derivatives (whenever these exist), are obtained. The relation neural networks radial basis approximations discussed. Numerical examples given purpose illustration.

参考文章(27)
G. Albano, V. Giorno, On the First Exit Time Problem for a Gompertz-Type Tumor Growth computer aided systems theory. ,vol. 5717, pp. 113- 120 ,(2009) , 10.1007/978-3-642-04772-5_16
Feilong Cao, Yongquan Zhang, Ze-Rong He, None, Interpolation and rates of convergence for a class of neural networks Applied Mathematical Modelling. ,vol. 33, pp. 1441- 1456 ,(2009) , 10.1016/J.APM.2008.02.009
Grzegorz Lewicki, G. Marino, Approximation by Superpositions of a Sigmoidal Function Zeitschrift Fur Analysis Und Ihre Anwendungen. ,vol. 22, pp. 463- 470 ,(2003) , 10.4171/ZAA/1156
Bum Il Hong, Nahmwoo Hahm, Approximation order to a function in C(R) by superposition of a sigmoidal function Applied Mathematics Letters. ,vol. 15, pp. 591- 597 ,(2002) , 10.1016/S0893-9659(02)80011-8
Xin Li, On simultaneous approximations by radial basis function neural networks Applied Mathematics and Computation. ,vol. 95, pp. 75- 89 ,(1998) , 10.1016/S0096-3003(97)10089-3
H.N. Mhaskar, C.A. Micchelli, Degree of Approximation by Neural and Translation Networks with a Single Hidden Layer Advances in Applied Mathematics. ,vol. 16, pp. 151- 183 ,(1995) , 10.1006/AAMA.1995.1008
Fred Brauer, Carlos Castillo-Chavez, Carlos Castillo-Chavez, Mathematical Models in Population Biology and Epidemiology ,(2001)
E. S. Chumerina, Choice of optimal strategy of tumor chemotherapy in Gompertz model Journal of Computer and Systems Sciences International. ,vol. 48, pp. 325- 331 ,(2009) , 10.1134/S1064230709020154