Group Equivariant Operators (GEOs) are a fundamental tool in the research on neural networks, since they make available a new kind of geometric knowledge engineering for deep learning, which can exploit symmetries in artificial intelligence and reduce the number of parameters required in the learning process. In this paper we introduce a new method to build non-linear GEOs and non-linear Group Equivariant Non-Expansive Operators (GENEOs), based on the concepts of symmetric function and permutant. This method is particularly interesting because of the good theoretical properties of GENEOs and the ease of use of permutants to build equivariant operators, compared to the direct use of the equivariance groups we are interested in. In our paper, we prove that the technique we propose works for any symmetric function, and benefits from the approximability of continuous symmetric functions by symmetric polynomials. A possible use in Topological Data Analysis of the GENEOs obtained by this new method is illustrated.
Conti, F., Frosini, P., Quercioli, N. (2022). On the Construction of Group Equivariant Non-Expansive Operators via Permutants and Symmetric Functions. FRONTIERS IN ARTIFICIAL INTELLIGENCE, 5, 1-11 [10.3389/frai.2022.786091].
On the Construction of Group Equivariant Non-Expansive Operators via Permutants and Symmetric Functions
Frosini, Patrizio
;Quercioli, Nicola
2022
Abstract
Group Equivariant Operators (GEOs) are a fundamental tool in the research on neural networks, since they make available a new kind of geometric knowledge engineering for deep learning, which can exploit symmetries in artificial intelligence and reduce the number of parameters required in the learning process. In this paper we introduce a new method to build non-linear GEOs and non-linear Group Equivariant Non-Expansive Operators (GENEOs), based on the concepts of symmetric function and permutant. This method is particularly interesting because of the good theoretical properties of GENEOs and the ease of use of permutants to build equivariant operators, compared to the direct use of the equivariance groups we are interested in. In our paper, we prove that the technique we propose works for any symmetric function, and benefits from the approximability of continuous symmetric functions by symmetric polynomials. A possible use in Topological Data Analysis of the GENEOs obtained by this new method is illustrated.File | Dimensione | Formato | |
---|---|---|---|
On the Construction of Group Equivariant Non-Expansive Operators via Permutants and Symmetric Functions_ARTICOLO_frai-05-786091.pdf
accesso aperto
Descrizione: Articolo principale
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione
833.73 kB
Formato
Adobe PDF
|
833.73 kB | Adobe PDF | Visualizza/Apri |
On the Construction of Group Equivariant Non-Expansive Operators via Permutants and Symmetric Functions_APPENDIX.pdf
accesso aperto
Descrizione: Appendice
Tipo:
Versione (PDF) editoriale
Licenza:
Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione
185.8 kB
Formato
Adobe PDF
|
185.8 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.