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.