Approximation problems in sigma-pi neural networks

李纯明, 陈天平 · 中国科学通报:英文版 · 1996

Let the function n: R~R→R be defined by Recently, approximating continuous function of several variables by the composition and superposition 9oπ of the function π and a function of one variable g is arousing great attention due to its applications in artificial neural networks (cf. references 1—3).

Read the paper · More papers on PaperTik