Density results by deep neural network operators with integer weights
In the present paper, a new family of multi-layers (deep) neural network (NN) operators is introduced. Density results have been established in the space of continuous functions on [−1,1], with respect to the uniform norm. First, the case of the operators with two-layers is considered in detail, th...
Main Author: | Danilo Costarelli |
---|---|
Format: | Article |
Language: | English |
Published: |
Vilnius Gediminas Technical University
2022-11-01
|
Series: | Mathematical Modelling and Analysis |
Subjects: | |
Online Access: | https://journals.vilniustech.lt/index.php/MMA/article/view/15974 |
Similar Items
-
Inverse Result of Approximation for the Max-Product Neural Network Operators of the Kantorovich Type and Their Saturation Order
by: Marco Cantarini, et al.
Published: (2021-12-01) -
Handling Vanishing Gradient Problem Using Artificial Derivative
by: Zheng Hu, et al.
Published: (2021-01-01) -
DPReLU: Dynamic Parametric Rectified Linear Unit and Its Proper Weight Initialization Method
by: Donghun Yang, et al.
Published: (2023-02-01) -
Nonparametric Estimation for High-Dimensional Space Models Based on a Deep Neural Network
by: Hongxia Wang, et al.
Published: (2023-09-01) -
Learnable Leaky ReLU (LeLeLU): An Alternative Accuracy-Optimized Activation Function
by: Andreas Maniatopoulos, et al.
Published: (2021-12-01)