This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network (C-RSN), an innovative variant of the Recurrent Spectral Network (RSN) model. The C-RSN model introduces localized non-linearity, complex fixed eigenvalues, and a distinct separation of memory and input processing functionalities. These features enable the C-RSN to evolve towards a dynamic, oscillating final state that bear some degree of similarity with biological cognition. The model’s ability to classify data through a time-dependent function, and the localization of information processing, is demonstrated by using the MNIST dataset. Remarkably, distinct items supplied as a sequential input yield patterns in time which bear the indirect imprint of the insertion order (and of the separation in time between contiguous insertions).

Complex Recurrent Spectral Network / Lorenzo Chicchi , Lorenzo Giambagli , Lorenzo Buffoni , Raffaele Marino , Duccio Fanelli. - In: CHAOS, SOLITONS & FRACTALS. - ISSN 1873-2887. - STAMPA. - 184:(2024), pp. 114998.1-114998.8. [10.1016/j.chaos.2024.114998]

Complex Recurrent Spectral Network

Lorenzo Chicchi
;
Lorenzo Giambagli;Lorenzo Buffoni;Raffaele Marino;Duccio Fanelli
2024

Abstract

This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network (C-RSN), an innovative variant of the Recurrent Spectral Network (RSN) model. The C-RSN model introduces localized non-linearity, complex fixed eigenvalues, and a distinct separation of memory and input processing functionalities. These features enable the C-RSN to evolve towards a dynamic, oscillating final state that bear some degree of similarity with biological cognition. The model’s ability to classify data through a time-dependent function, and the localization of information processing, is demonstrated by using the MNIST dataset. Remarkably, distinct items supplied as a sequential input yield patterns in time which bear the indirect imprint of the insertion order (and of the separation in time between contiguous insertions).
2024
184
1
8
Lorenzo Chicchi , Lorenzo Giambagli , Lorenzo Buffoni , Raffaele Marino , Duccio Fanelli
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0960077924005502-main.pdf

Accesso chiuso

Tipologia: Pdf editoriale (Version of record)
Licenza: Tutti i diritti riservati
Dimensione 1.72 MB
Formato Adobe PDF
1.72 MB Adobe PDF   Richiedi una copia

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

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1360914
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact