Empirical study of the modulus as activation function in computer vision applications
Authors:
- Iván Vallés-PérezIVIván Vallés-Pérez
- Emilio Soria-OlivasEmilio Soria-Olivas
- Marcelino Martínez-SoberMarcelino Martínez-Sober
- Antonio J. Serrano-LópezAntonio J. Serrano-López
- Joan Vila-FrancésJVJoan Vila-Francés
- Juan Gómez-SanchísJGJuan Gómez-Sanchís
Open Access
- 18 January 2023
- journal article
- research article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 120
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Ministerio de Ciencia e Innovación
- Agencia Estatal de Investigación (PID2019-107347RR-C33, PID2021-127946OB-I00)
This publication has 7 references indexed in Scilit:
- Activation functions in deep learning: A comprehensive survey and benchmarkNeurocomputing, 2022
- RSigELU: A nonlinear activation function for deep neural networksExpert Systems with Applications, 2021
- PFLU and FPFLU: Two novel non-monotonic activation functions in convolutional neural networksNeurocomputing, 2021
- TinyML-Enabled Frugal Smart Objects: Challenges and OpportunitiesIEEE Circuits and Systems Magazine, 2020
- Dying ReLU and Initialization: Theory and Numerical ExamplesCommunications in Computational Physics, 2020
- Artificial neural networks in hardware: A survey of two decades of progressNeurocomputing, 2010
- The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem SolutionsInternational Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 1998