Saeed Panahian Fard

Double approximate identity neural networks universal approximation in real lebesgue spaces

The aim of this study is to investigate that some classes of feedforward neural networks exist such that they have universal approximation property. Based on the double approximate identity a main theorem is presented. The result shows the universal approximation capability of double approximate identity neural networks in real two dimensional compact Lebesgue integrable subspaces.

On the Universal Approximation Capability of Flexible Approximate Identity Neural Networks

This study presents some class of feedforward neural networks to investigate the universal approximation capability of continuous flexible functions. Based on the flexible approximate identity, some theorems are constructed. The results are provided to demonstrate the universal approximation capability of flexible approximate identity neural networks to any continuous flexible function.

The Universal Approximation Capability of Double Flexible Approximate Identity Neural Networks

This study investigates the universal approximation capability of three-layer feedforward double flexible approximate identity neural networks in the space of continuous functions with two variables. First, we propose double flexible approximate identity functions, which are a combination of double approximate identity functions and flexible approximate identity functions as investigated in our previous studies. Then, we prove that any continuous function f with two variables will converge to itself if it convolves with double flexible approximate identity. Finally, we prove a main theorem by using the obtained results.

The universal approximation capabilities of mellin approximate identity neural networks

Universal approximation capability of feedforward neural networks with one hidden layer states that these networks are dense in the space of functions. In this paper, the concept of the Mellin approximate identity functions is proposed. By using this concept, It is shown that feedforward Mellin approximate identity neural networks with one hidden layer can approximate any positive real continuous function to any degree of accuracy. Moreover, universal approximation capability of these networks is extended to positive real Lebesgue spaces.

The universal approximation capabilities of double 2 ∏-periodic approximate identity neural networks

The purpose of this study is to investigate the universal approximation capabilities of a certain class of single-hidden-layer feedforward neural networks, which is called double 2

Interval type-2 fuzzy neural networks version of the Stone-Weierstrass theorem

\pi

Spherical approximate identity neural networks are universal approximators

π-periodic approximate identity neural networks. Using double 2