The storage capacity of an autoassociative memory with extremely diluted connectivity and with threshold-linear elementary units is studied in its dependence on the graded structure and on the sparseness of the coding scheme, and on the form of the learning rule used. As the coding becomes sparse, more patterns can be stored, and the difference in capacity (measured for a given number of modifiable synapses per unit) between fully connected and highly diluted systems vanishes. Graded (non-binary) codings, especially when used with learning rules nonlinear in their post-synaptic factor, further increase the number of patterns that can be stored by making their retrieved representation even sparser.

Dilution and sparse coding in threshold-linear nets / Treves, Alessandro. - In: JOURNAL OF PHYSICS. A, MATHEMATICAL AND GENERAL. - ISSN 0305-4470. - 24:1(1991), pp. 327-335. [10.1088/0305-4470/24/1/038]

Dilution and sparse coding in threshold-linear nets

Treves, Alessandro
1991

Abstract

The storage capacity of an autoassociative memory with extremely diluted connectivity and with threshold-linear elementary units is studied in its dependence on the graded structure and on the sparseness of the coding scheme, and on the form of the learning rule used. As the coding becomes sparse, more patterns can be stored, and the difference in capacity (measured for a given number of modifiable synapses per unit) between fully connected and highly diluted systems vanishes. Graded (non-binary) codings, especially when used with learning rules nonlinear in their post-synaptic factor, further increase the number of patterns that can be stored by making their retrieved representation even sparser.
24
1
327
335
http://iopscience.iop.org/article/10.1088/0305-4470/24/1/038/meta
Treves, Alessandro
File in questo prodotto:
File Dimensione Formato  
Tre91a.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Non specificato
Dimensione 378.97 kB
Formato Adobe PDF
378.97 kB 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/20.500.11767/85748
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 30
  • ???jsp.display-item.citation.isi??? 24
social impact