Empirical study of the modulus as activation function in computer vision applications

In this work we propose a new non-monotonic activation function: the modulus. The majority of the reported research on nonlinearities is focused on monotonic functions. We empirically demonstrate how by using the modulus activation function on computer vision tasks the models generalize better than...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Engineering applications of artificial intelligence 2023-04, Vol.120, p.105863, Article 105863
Hauptverfasser: Vallés-Pérez, Iván, Soria-Olivas, Emilio, Martínez-Sober, Marcelino, Serrano-López, Antonio J., Vila-Francés, Joan, Gómez-Sanchís, Juan
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this work we propose a new non-monotonic activation function: the modulus. The majority of the reported research on nonlinearities is focused on monotonic functions. We empirically demonstrate how by using the modulus activation function on computer vision tasks the models generalize better than with other nonlinearities — up to a 15% accuracy increase in CIFAR100 and 4% in CIFAR10, relative to the best of the benchmark activations tested. With the proposed activation function the vanishing gradient and dying neurons problems disappear, because the derivative of the activation function is always 1 or −1. The simplicity of the proposed function and its derivative make this solution specially suitable for TinyML and hardware applications.
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2023.105863