随着人工神经网络(ANN)理论和技术的不断发展,人们加深了对高阶神经网络映射能力的研究。本文对高阶神经网络实现有限集A(?)R~n→有限集B(?)R的函数逼近问题进行了理论上的研究,得出了高阶神经网络可以实现任何有限集到有限集函数逼近的结论。 With the continuous development of artificial neural network (ANN) theory and technology, people have deepened their research on the mapping ability of high-order neural networks. In this paper, we theoretically study the function approximation of the finite-set A (?) R ~ n → finite set B (?) R for high-order neural networks, and find that the high-order neural network can realize any finite set to finite set The conclusion of the function approximation.