arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.02302math.NAcs.LGcs.NA
收藏

具有准最优多项式逼近率的深度神经网络分析

Analysis of Deep Neural Networks with Quasi-optimal polynomial approximation rates

The University of Tennessee(田纳西大学)

Joseph Daws, Clayton Webster

摘要:

我们展示了一个能够近似一大类高维近似的深度神经网络的存在。建议的神经网络的建设是基于准最佳的多项式逼近。我们表明,该网络实现了一个差错率,是次指数的多项式函数,$M$,用于多项式逼近的数量。实现该次指数速率的网络的复杂性在$M$中被证明是代数的。

英文摘要:

We show the existence of a deep neural network capable of approximating a wide class of high-dimensional approximations. The construction of the proposed neural network is based on a quasi-optimal polynomial approximation. We show that this network achieves an error rate that is sub-exponential in the number of polynomial functions, $M$, used in the polynomial approximation. The complexity of the network which achieves this sub-exponential rate is shown to be algebraic in $M$.

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。

↑