Abstract In this work we study a Hebbian neural network, where neurons are arranged according to a hierarchical architecture such that their couplings scale with their reciprocal distance. As a full statistical mechanics solution is not yet available, after a streamlined introduction to the state of the art via that route, the problem is consistently approached through signal-to-noise technique and extensive numerical simulations. Focusing on the low-storage regime, where the amount of stored patterns grows at most logarithmical with the system size, we prove that these non-mean-field Hopfield-like networks display a richer phase diagram than their classical counterparts. In particular, these networks are able to perform serial processing (i.e. retrieve one pattern at a time through a complete rearrangement of the whole ensemble of neurons) as well as parallel processing (i.e. retrieve several patterns simultaneously, delegating the management of different patterns to diverse communities that build network). The tune between the two regimes is given by the rate of the coupling decay and by the level of noise affecting the system. The price to pay for those remarkable capabilities lies in a network’s capacity smaller than the mean field counterpart, thus yielding a new budget principle: the wider the multitasking capabilities, the lower the network load and vice versa. This may have important implications in our understanding of biological complexity.

Hierarchical neural networks perform both serial and parallel processing / Agliari, Elena; Barra, Adriano; Galluzzi, Andrea; Guerra, Francesco; Tantari, Daniele; Tavani, Flavia. - In: NEURAL NETWORKS. - ISSN 0893-6080. - STAMPA. - 66:(2015), pp. 22-35. [10.1016/j.neunet.2015.02.010]

Hierarchical neural networks perform both serial and parallel processing

AGLIARI, ELENA;BARRA, ADRIANO;GALLUZZI, ANDREA;GUERRA, Francesco;TANTARI, DANIELE;TAVANI, FLAVIA
2015

Abstract

Abstract In this work we study a Hebbian neural network, where neurons are arranged according to a hierarchical architecture such that their couplings scale with their reciprocal distance. As a full statistical mechanics solution is not yet available, after a streamlined introduction to the state of the art via that route, the problem is consistently approached through signal-to-noise technique and extensive numerical simulations. Focusing on the low-storage regime, where the amount of stored patterns grows at most logarithmical with the system size, we prove that these non-mean-field Hopfield-like networks display a richer phase diagram than their classical counterparts. In particular, these networks are able to perform serial processing (i.e. retrieve one pattern at a time through a complete rearrangement of the whole ensemble of neurons) as well as parallel processing (i.e. retrieve several patterns simultaneously, delegating the management of different patterns to diverse communities that build network). The tune between the two regimes is given by the rate of the coupling decay and by the level of noise affecting the system. The price to pay for those remarkable capabilities lies in a network’s capacity smaller than the mean field counterpart, thus yielding a new budget principle: the wider the multitasking capabilities, the lower the network load and vice versa. This may have important implications in our understanding of biological complexity.
multitasking associative networks
01 Pubblicazione su rivista::01a Articolo in rivista
Hierarchical neural networks perform both serial and parallel processing / Agliari, Elena; Barra, Adriano; Galluzzi, Andrea; Guerra, Francesco; Tantari, Daniele; Tavani, Flavia. - In: NEURAL NETWORKS. - ISSN 0893-6080. - STAMPA. - 66:(2015), pp. 22-35. [10.1016/j.neunet.2015.02.010]
File allegati a questo prodotto
File Dimensione Formato  
Agliari_Hierarchical-neural_2015.pdf

solo gestori archivio

Note: Versione dell'editore
Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.01 MB
Formato Adobe PDF
1.01 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Agliari_preprint_Hierarchical-neural_2015.pdf

accesso aperto

Tipologia: Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza: Creative commons
Dimensione 1.28 MB
Formato Unknown
1.28 MB Unknown Visualizza/Apri PDF
ABGGTT-NN2015.pdf

solo gestori archivio

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.18 MB
Formato Adobe PDF
1.18 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

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/11573/782048
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 15
social impact