Choquet Capacity networks for random point process classification - Morphologie mathématique (CMM) Access content directly
Preprints, Working Papers, ... Year : 2023

Choquet Capacity networks for random point process classification

Abstract

In this study, we revisit the Choquet capacity in the framework of convolutional neural networks, in (max, +)-algebra. By incorporating a discrete and learnable Choquet capacity model, we enhance the ability to represent the spatial arrangement and density variations in random point processes of convolutional neural networks. To validate the effectiveness of our approach, numerical experiments are conducted on synthetic datasets simulating diverse spatial point patterns of the Neyman-Scott process. When compared to classical convolutional neural networks, the proposed approach exhibits comparable or improved performances in terms of classification. Superior results are also observed in regression problems involving the Neyman-Scott parameter that monitors the point patterns spatial dispersion.
Fichier principal
Vignette du fichier
ccn_v2.pdf (664.68 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04250560 , version 1 (19-10-2023)
hal-04250560 , version 2 (09-01-2024)

Licence

Copyright

Identifiers

  • HAL Id : hal-04250560 , version 2

Cite

Mehran Mohammadi, Santiago Velasco-Forero, François Willot, Mateus Sangalli, Thomas Walter, et al.. Choquet Capacity networks for random point process classification. 2024. ⟨hal-04250560v2⟩
105 View
31 Download

Share

Gmail Facebook X LinkedIn More