Optimising synaptic learning rules in linear associative memories (Q1182329): Difference between revisions
From MaRDI portal
Removed claim: author (P16): Item:Q853284 |
ReferenceBot (talk | contribs) Changed an Item |
||
(3 intermediate revisions by 3 users not shown) | |||
Property / author | |||
Property / author: Peter Dayan / rank | |||
Normal rank | |||
Property / MaRDI profile type | |||
Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank | |||
Property / Wikidata QID | |||
Property / Wikidata QID: Q52102309 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q4403756 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: The space of interactions in neural network models / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Neural networks and physical systems with emergent collective computational abilities. / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Q3992681 / rank | |||
Normal rank | |||
Property / cites work | |||
Property / cites work: Correlation Matrix Memories / rank | |||
Normal rank |
Latest revision as of 14:57, 15 May 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Optimising synaptic learning rules in linear associative memories |
scientific article |
Statements
Optimising synaptic learning rules in linear associative memories (English)
0 references
28 June 1992
0 references
A model of associative matrix memory incorporating 4 numbers, defining a learning rule, is considered. The maximization of the signal-to-noise ratio is used as a criterion for optimization of the form of the learning rule of the model. A well known covariance rule is shown to be optimal. Two other rules, previously suggested, are shown to be asymptotically optimal. All three rules, however, are shown to be strongly biologically irrelevant. Some explanation for this discrepancy and further discussion is proposed.
0 references
synaptic learning rules
0 references
linear associative memories
0 references
associative matrix memory
0 references
learning rule
0 references
maximization of the signal-to-noise ratio
0 references
covariance rule
0 references