In the framework of discontinuous function approximation and discontinuity interface detection, we consider an approach involving Neural Networks. In particular, we define a novel typology of Neural Network layers endowed with new learnable parameters and discontinuities in the space of the activations. These layers allow to create a completely new kind of Neural Networks, characterized to be discontinuous, not only able to approximate discontinuous functions but also to learn and detect the discontinuity interfaces. A sound theoretical analysis concerning the properties of the new discontinuous layers is performed, and some tests on discontinuous functions are proposed, in order to assess the potential of such instruments.

Discontinuous Neural Networks and Discontinuity Learning / Della, Santa; Pieraccini, Sandra. - In: JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS. - ISSN 0377-0427. - ELETTRONICO. - 419:(2023), p. 114678. [10.1016/j.cam.2022.114678]

Discontinuous Neural Networks and Discontinuity Learning

della santa;pieraccini
2023

Abstract

In the framework of discontinuous function approximation and discontinuity interface detection, we consider an approach involving Neural Networks. In particular, we define a novel typology of Neural Network layers endowed with new learnable parameters and discontinuities in the space of the activations. These layers allow to create a completely new kind of Neural Networks, characterized to be discontinuous, not only able to approximate discontinuous functions but also to learn and detect the discontinuity interfaces. A sound theoretical analysis concerning the properties of the new discontinuous layers is performed, and some tests on discontinuous functions are proposed, in order to assess the potential of such instruments.
File in questo prodotto:
File Dimensione Formato  
DiscNN_main.pdf

accesso aperto

Tipologia: 1. Preprint / submitted version [pre- review]
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 2.15 MB
Formato Adobe PDF
2.15 MB Adobe PDF Visualizza/Apri
Manuscript_elsarticle.pdf

embargo fino al 18/02/2024

Descrizione: Post print
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Creative commons
Dimensione 4.57 MB
Formato Adobe PDF
4.57 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Discontinuity_learning_final_file.pdf

non disponibili

Descrizione: Versione editoriale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 4.47 MB
Formato Adobe PDF
4.47 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2851043