Smoothing piecewise linear activation functions based on mollified square root functions

DOI10.3934/MFC.2023032MaRDI QIDQ6633224

Junli Zhao, Guangyu Yang, Jieyu Ding, Tony Yuxiang Pan

Publication date: 5 November 2024

Published in: Mathematical Foundations of Computing (Search for Journal in Brave)

zbMATH Keywords

smoothnesspiecewise linear functionsactivation functionsmollified square root functions

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15)

Cites Work

• Multilayer feedforward networks are universal approximators
• Approximating functions with multi-features by deep convolutional neural networks
• Approximation by superpositions of a sigmoidal function
• A survey on modern trainable activation functions
• Fast Global Minimization of the Active Contour/Snake Model

This page was built for publication: Smoothing piecewise linear activation functions based on mollified square root functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6633224)