Approximation results on neural network operators of convolution type

2025/03/28 by Asiye Arif, Arif, Asiye, T. Yurdakadim +1 · 1 citation
Computer Science · Mathematics · #41A17 #41A25 #41A35 #47A58 #Approximation Theory and Sequence Spaces #FOS: Mathematics #Fuzzy Logic and Control Systems #Neural Networks and Applications #Numerical Analysis (math.NA)

paper · pdf · doi:10.48550/arxiv.2503.22301

openalex publication_date 2025/03/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In the present paper, we introduce three neural network operators of convolution type activated by symmetrized, deformed and parametrized B-generalized logistic function. We deal with the approximation properties of these operators to the identity by using modulus of continuity. Furthermore, we show that our operators preserve global smoothness and consider the iterated versions of them. Here, we find it is worthy to mention that these operators play important roles in neural network approximation since most of the basic network models are activated by logistic functions.

Cited by

• Approximation by neural network operators of convolution type activated by deformed and parametrized half hyperbolic tangent function

Related

• Approximation by Exponential Type Neural Network Operators
• Approximation by neural network operators of convolution type activated by deformed and parametrized half hyperbolic tangent function
• Approximation by Neural Network operators in L^p spaces associated with an arbitrary measure
• Approximation by Steklov Neural Network Operators
• Approximation bounds for convolutional neural networks in operator learning