MorphoActivation: Generalizing ReLU activation function by mathematical morphology - Archive ouverte HAL Access content directly
Conference Papers Year :

MorphoActivation: Generalizing ReLU activation function by mathematical morphology

Jesús Angulo

Abstract

This paper analyses both nonlinear activation functions and spatial max-pooling for Deep Convolutional Neural Networks (DCNNs) by means of the algebraic basis of mathematical morphology. Additionally, a general family of activation functions is proposed by considering both max-pooling and nonlinear operators in the context of morphological representations. Experimental section validates the goodness of our approach on classical benchmarks for supervised learning by DCNN.
Fichier principal
Vignette du fichier
MorphoActivationsDGMM20.pdf (897.81 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03721056 , version 1 (12-07-2022)

Identifiers

Cite

Santiago Velasco-Forero, Jesús Angulo. MorphoActivation: Generalizing ReLU activation function by mathematical morphology. International Conference on Discrete Geometry and Mathematical Morphology, Oct 2022, Strasbourg, France. ⟨hal-03721056⟩
35 View
71 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More