Most analytical results concerning the long-time behaviour of associative memory networks have been obtained by using binary elementary units. The use of alternative types of neuron-like processing elements is considered as a way of testing the generality of those results and of approaching biological realism. In particular, threshold-linear units are proposed as appropriate in models designed to reproduce low firing rates, in which long-time stability does not rely on single unit saturation. Such units are simple enough to allow detailed analytical understanding of the properties of the network. This is demonstrated by analysing the attractor states of a network operating at low rates. It is shown that while the interesting retrieval behaviour persists, the roles of the different parameters as well as the nature of the stable states change completely with respect to the binary implementation.

Threshold-linear formal neurons in auto-associative nets / Treves, Alessandro. - In: JOURNAL OF PHYSICS. A, MATHEMATICAL AND GENERAL. - ISSN 0305-4470. - 23:12(1990), pp. 2631-2650. [10.1088/0305-4470/23/12/037]

Threshold-linear formal neurons in auto-associative nets

Treves, Alessandro
1990

Abstract

Most analytical results concerning the long-time behaviour of associative memory networks have been obtained by using binary elementary units. The use of alternative types of neuron-like processing elements is considered as a way of testing the generality of those results and of approaching biological realism. In particular, threshold-linear units are proposed as appropriate in models designed to reproduce low firing rates, in which long-time stability does not rely on single unit saturation. Such units are simple enough to allow detailed analytical understanding of the properties of the network. This is demonstrated by analysing the attractor states of a network operating at low rates. It is shown that while the interesting retrieval behaviour persists, the roles of the different parameters as well as the nature of the stable states change completely with respect to the binary implementation.
23
12
2631
2650
http://iopscience.iop.org/article/10.1088/0305-4470/23/12/037/meta
Treves, Alessandro
File in questo prodotto:
File Dimensione Formato  
Tre90a.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Non specificato
Dimensione 1.14 MB
Formato Adobe PDF
1.14 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/20.500.11767/85742
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 36
  • ???jsp.display-item.citation.isi??? 30
social impact