Thumbnail
Access Restriction
Open

Author Elengler, Johannes ♦ Esteger, Angelika ♦ Eeinarsson, Hafsteinn
Source Directory of Open Access Journals (DOAJ)
Content type Text
Publisher Frontiers Media S.A.
File Format HTM / HTML
Date Created 2015-09-11
Copyright Year ©2014
Language English
Subject Domain (in LCC) RC321-571
Subject Keyword Neuropsychiatry ♦ Biological psychiatry ♦ Neurosciences ♦ One shot learning ♦ Relation Learning ♦ Bootstrap Percolation and Propagation ♦ Hetero-associative Network ♦ Memory capacity ♦ Internal medicine ♦ Medicine ♦ Association Learning
Abstract We present a high-capacity model for one-shot association learning(hetero-associative memory) in sparse networks. We assume that basic patternsare pre-learned in networks and associations between two patterns are presentedonly once and have to be learned immediately. The model is a combination of anAmit-Fusi like network sparsely connected to a Willshaw type network. Thelearning procedure is palimpsest and comes from earlier work on one-shotpattern learning. However, in our setup we can enhance the capacity of thenetwork by iterative retrieval. This yields a model for sparse brain-likenetworks in which populations of a few thousand neurons are capable of learninghundreds of associations even if they are presented only once. The analysis ofthe model is based on a novel result by Janson et. al. on bootstrappercolation in random graphs.
ISSN 16625188
Age Range 18 to 22 years ♦ above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 2014-11-01
e-ISSN 16625188
Journal Frontiers in Computational Neuroscience
Volume Number 8


Source: Directory of Open Access Journals (DOAJ)