Neural Networks ( IF 6.0 ) Pub Date : 2020-07-22 , DOI: 10.1016/j.neunet.2020.07.021 Eduardo Paluzo-Hidalgo 1 , Rocio Gonzalez-Diaz 1 , Miguel A Gutiérrez-Naranjo 2
It is well-known that artificial neural networks are universal approximators. The classical existence result proves that, given a continuous function on a compact set embedded in an -dimensional space, there exists a one-hidden-layer feed-forward network that approximates the function. In this paper, a constructive approach to this problem is given for the case of a continuous function on triangulated spaces. Once a triangulation of the space is given, a two-hidden-layer feed-forward network with a concrete set of weights is computed. The level of the approximation depends on the refinement of the triangulation.
中文翻译:
两层前馈网络是通用逼近器:一种构造方法。
众所周知,人工神经网络是通用近似器。经典的存在结果证明,在嵌入到在三维空间中,存在一个逼近该函数的单层前馈网络。在本文中,针对三角空间上的连续函数,给出了针对此问题的构造方法。一旦给定了空间的三角剖分,就会计算出具有特定权重集的两层前馈网络。近似程度取决于三角剖分的细化程度。