MorphoActivation: Generalizing ReLU activation function by mathematical morphology

Santiago Velasco-Forero, Jesús Angulo
7/13/2022
cs.LGcs.DMeess.IV

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

TSSR: A Truncated and Signed Square Root Activation Function for Neural Networks

83% match2023

Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks

80% match2024

Feed-Forward Neural Networks as a Mixed-Integer Program

80% match2024

Sparse Hybrid Linear-Morphological Networks

80% match1 repo2025

Deep Learning Activation Functions: Fixed-Shape, Parametric, Adaptive, Stochastic, Miscellaneous, Non-Standard, Ensemble

79% match2024

Training Deep Morphological Neural Networks as Universal Approximators

79% match2025

Cite this paper

@article{velascoforero2022morphoactivation,
  title  = {MorphoActivation: Generalizing ReLU activation function by mathematical morphology},
  author = {Santiago Velasco-Forero and Jesús Angulo},
  year   = {2022},
  eprint = {2207.06413},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.06413v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.06413.svg)](https://codeofpaper.com/paper/2207.06413)

Discussion