Exponential convergence of the deep neural network approximation for analytic functions
نویسندگان
چکیده
منابع مشابه
Approximation of analytic functions : a method of enhanced convergence
We present a method of enhanced convergence for the approximation of analytic functions. This method introduces conformal transformations in the approximation problems in order to help extract the values of a given analytic function from its Taylor expansion. We show that conformal transformations can extend the radius of convergence of a power series far into infinity, enhance substantially it...
متن کاملNeural Networks for Optimal Approximation of Smooth and Analytic Functions
We prove that neural networks with a single hidden layer are capable of providing an optimal order of approximation for functions assumed to possess a given number of derivatives, if the activation function evaluated by each principal element satisfies certain technical conditions. Under these conditions, it is also possible to construct networks that provide a geometric order of approximation ...
متن کاملThe Fractional Differential Polynomial Neural Network for Approximation of Functions
In this work, we introduce a generalization of the differential polynomial neural network utilizing fractional calculus. Fractional calculus is taken in the sense of the Caputo differential operator. It approximates a multi-parametric function with particular polynomials characterizing its functional output as a generalization of input patterns. This method can be employed on data to describe m...
متن کاملDeep Neural Network Approximation using Tensor Sketching
Deep neural networks are powerful learning models that achieve state-of-the-art performance on many computer vision, speech, and language processing tasks. In this paper, we study a fundamental question that arises when designing deep network architectures: Given a target network architecture can we design a “smaller” network architecture that “approximates” the operation of the target network?...
متن کاملApproximation of Analytic Functions by Chebyshev Functions
and Applied Analysis 3 where we refer to 1.4 for the am’s and we follow the convention ∏m−1 j m · · · 1. We can easily check that cm’s satisfy the following relation: m 2 m 1 cm 2 − ( m2 − n2 ) cm am 2.2 for any m ∈ {0, 1, 2, . . .}. Theorem 2.1. Assume that n is a positive integer and the radius of convergence of the power series ∑∞ m 0 amx m is ρ > 0. Let ρ0 min{1, ρ}. Then, every solution y ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Science China Mathematics
سال: 2018
ISSN: 1674-7283,1869-1862
DOI: 10.1007/s11425-018-9387-x