arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1708.06219cs.NEcs.ITcs.NAmath.ITmath.NA
收藏

关于用固定权重单隐层前馈神经网络进行逼近

On the approximation by single hidden layer feedforward neural networks with fixed weights

Institute of Mathematics and Mechanics, Azerbaijan National Academy of Sciences(阿塞拜疆国家科学院数学与力学研究所)

Namig J. Guliyev, Vugar E. Ismailov

AI总结:

本文证明固定权重单隐层前馈神经网络能逼近任意连续函数,但无法逼近所有连续多变量函数。

摘要:

前馈神经网络因其通用逼近性质在各学科中广泛应用。一些作者证明,当被逼近函数为单变量时,固定权重单隐层前馈神经网络(SLFNs)仍具有通用逼近性质,但此现象不限制隐层神经元数量。隐层神经元数量越多,网络给出精确结果的概率越高。本文构造性地证明,固定权重为1且隐层有两个神经元的SLFNs能逼近实数集紧致子集上的任意连续函数。该结果在各种数值示例中得到了应用。最后,本文展示固定权重的SLFNs无法逼近所有连续多变量函数。

英文摘要:

Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) with fixed weights still possess the universal approximation property provided that approximated functions are univariate. But this phenomenon does not lay any restrictions on the number of neurons in the hidden layer. The more this number, the more the probability of the considered network to give precise results. In this note, we constructively prove that SLFNs with the fixed weight $1$ and two neurons in the hidden layer can approximate any continuous function on a compact subset of the real line. The applicability of this result is demonstrated in various numerical examples. Finally, we show that SLFNs with fixed weights cannot approximate all continuous multivariate functions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑