arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.09181cs.NEcs.ITcs.NAmath.ITmath.NA
收藏

两个固定权值隐层前馈神经网络的逼近能力

Approximation capability of two hidden layer feedforward neural networks with fixed weights

Namig J. Guliyev, Vugar E. Ismailov

摘要:

我们通过算法构造了一个两隐层前馈神经网络(TLFN)模型,其权值固定为$d$维欧氏空间的单位坐标向量,总隐层神经元数为$3d+2$,可以任意精度逼近任意连续$d$ -变量函数.该结果特别显示了TLFN模型优于单隐层前馈神经网络(SLFN)模型的优点,因为具有固定权重的SLFN不具有逼近多变量函数的能力。

英文摘要:

We algorithmically construct a two hidden layer feedforward neural network (TLFN) model with the weights fixed as the unit coordinate vectors of the $d$-dimensional Euclidean space and having $3d+2$ number of hidden neurons in total, which can approximate any continuous $d$-variable function with an arbitrary precision. This result, in particular, shows an advantage of the TLFN model over the single hidden layer feedforward neural network (SLFN) model, since SLFNs with fixed weights do not have the capability of approximating 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。

↑