We compute the homogeneous ideals of varieties, in a projective space of tensors, associated to different choices of the Boolean operators that describe the decision process in small neural networks. We prove that, starting with networks with three nodes, the varieties associated to different Boolean operators are all distinct.
Marziali, S. (2024). Boolean operators and neural networks. ANNALI DELL'UNIVERSITÀ DI FERRARA. SEZIONE 7: SCIENZE MATEMATICHE, 70(4), 1767-1783 [10.1007/s11565-024-00541-5].
Boolean operators and neural networks
Marziali, Sara
2024-01-01
Abstract
We compute the homogeneous ideals of varieties, in a projective space of tensors, associated to different choices of the Boolean operators that describe the decision process in small neural networks. We prove that, starting with networks with three nodes, the varieties associated to different Boolean operators are all distinct.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
s11565-024-00541-5.pdf
accesso aperto
Tipologia:
PDF editoriale
Licenza:
Creative commons
Dimensione
461.09 kB
Formato
Adobe PDF
|
461.09 kB | Adobe PDF | Visualizza/Apri |
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/11365/1276706