Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at https://www.ucl.ac.uk/finance/research/rs-contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Optimising synaptic learning rules in linear associative memories.
  • Publication Type:
    Journal article
  • Publication Sub Type:
    Journal Article
  • Authors:
    Dayan P, Willshaw DJ
  • Publication date:
  • Pagination:
    253, 265
  • Journal:
    Biol Cybern
  • Volume:
  • Issue:
  • Status:
  • Country:
  • Print ISSN:
  • Language:
  • Keywords:
    Animals, Association Learning, Learning, Mathematics, Memory, Models, Neurological, Models, Psychological, Synapses
Associative matrix memories with real-valued synapses have been studied in many incarnations. We consider how the signal/noise ratio for associations depends on the form of the learning rule, and we show that a covariance rule is optimal. Two other rules, which have been suggested in the neurobiology literature, are asymptotically optimal in the limit of sparse coding. The results appear to contradict a line of reasoning particularly prevalent in the physics community. It turns out that the apparent conflict is due to the adoption of different underlying models. Ironically, they perform identically at their co-incident optima. We give details of the mathematical results, and discuss some other possible derivations and definitions of the signal/noise ratio.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
There are no UCL People associated with this publication
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by