Heaviside function as an activation function
- 26 October 2022
- journal article
- research article
- Published by Walter de Gruyter GmbH in Journal of Applied Analysis
- Vol. 29 (1) , 1-2
Abstract
The uniform closure of the neural networks with Heaviside activation is specified.Keywords
Funding Information
- Japan Society for the Promotion of Science (19K14581, 19K03546)
This publication has 6 references indexed in Scilit:
- A Global Universality of Two-Layer Neural Networks with ReLU ActivationsJournal of Function Spaces, 2021
- Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU ActivationsMathematics, 2019
- Neural network with unbounded activation functions is universal approximatorApplied and Computational Harmonic Analysis, 2017
- Best approximation by Heaviside perceptron networksNeural Networks, 2000
- Approximation theory of the MLP model in neural networksActa Numerica, 1999
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989