论文标题
三层神经网络可以代表任何多元功能
A three layer neural network can represent any multivariate function
论文作者
论文摘要
1987年，Hecht-Nielsen表明，任何连续的多元函数都可以通过某个类型的三层神经网络来实现。该结果在神经网络文献中进行了很大的讨论。在本文中，我们证明，不仅可以连续功能，而且所有不连续的功能都可以由此类神经网络实施。
In 1987, Hecht-Nielsen showed that any continuous multivariate function can be implemented by a certain type three-layer neural network. This result was very much discussed in neural network literature. In this paper we prove that not only continuous functions but also all discontinuous functions can be implemented by such neural networks.
