Matches in SemOpenAlex for { <https://semopenalex.org/work/W2058139211> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2058139211 endingPage "854" @default.
- W2058139211 startingPage "845" @default.
- W2058139211 abstract "We propose learning and forgetting techniques for the generalized brain-state-in-a-box (BSB) based associative memories. A generalization of the BSB model allows each neuron to have its own bias and the synaptic weight matrix does not have to be symmetric. A pattern is learned by a memory if its noisy or an incomplete version presented to the memory is mapped back to this pattern. A pattern, previously stored, is forgotten or deleted from the memory if a stimulus that is a perturbed version of the pattern, when presented to the memory, is not mapped back to this pattern. In this paper we propose on-line memory storage and deletion methods using an iterative method of computing the pseudo-inverse of a given matrix. The proposed methods allow one to add or delete a memory pattern by updating, rather than recomputing from scratch, the current synaptic weight matrix in a single step. We first analyze the desired characteristics of neural network associative memories. After that, we review the existing methods for design of neural associative memories. Then we discuss the generalized BSB neural model and its possible function as an associative memory and proffer arguments in support of using such models for neural associative memories. In particular, the generalized BSB type models are easier to analyze, synthesize, and implement than other neural networks. The results obtained are illustrated by numerical examples. Copyright 1996 Elsevier Science Ltd" @default.
- W2058139211 created "2016-06-24" @default.
- W2058139211 creator A5009616191 @default.
- W2058139211 creator A5030671518 @default.
- W2058139211 creator A5046812485 @default.
- W2058139211 date "1996-07-01" @default.
- W2058139211 modified "2023-10-18" @default.
- W2058139211 title "Learning and Forgetting in Generalized Brain-state-in-a-box (BSB) Neural Associative Memories" @default.
- W2058139211 cites W1765000751 @default.
- W2058139211 cites W1964718849 @default.
- W2058139211 cites W1968012884 @default.
- W2058139211 cites W1992172913 @default.
- W2058139211 cites W1995114494 @default.
- W2058139211 cites W1995889551 @default.
- W2058139211 cites W1996773027 @default.
- W2058139211 cites W2003137566 @default.
- W2058139211 cites W2033788889 @default.
- W2058139211 cites W2036270456 @default.
- W2058139211 cites W2074542862 @default.
- W2058139211 cites W2078510115 @default.
- W2058139211 cites W2084067660 @default.
- W2058139211 cites W2100885571 @default.
- W2058139211 cites W2112246162 @default.
- W2058139211 cites W2127098738 @default.
- W2058139211 cites W2128084896 @default.
- W2058139211 cites W2139088408 @default.
- W2058139211 cites W2140575957 @default.
- W2058139211 cites W2147311265 @default.
- W2058139211 cites W2153579835 @default.
- W2058139211 cites W2341005672 @default.
- W2058139211 cites W37611134 @default.
- W2058139211 doi "https://doi.org/10.1016/0893-6080(95)00101-8" @default.
- W2058139211 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/12662567" @default.
- W2058139211 hasPublicationYear "1996" @default.
- W2058139211 type Work @default.
- W2058139211 sameAs 2058139211 @default.
- W2058139211 citedByCount "21" @default.
- W2058139211 countsByYear W20581392112012 @default.
- W2058139211 countsByYear W20581392112018 @default.
- W2058139211 crossrefType "journal-article" @default.
- W2058139211 hasAuthorship W2058139211A5009616191 @default.
- W2058139211 hasAuthorship W2058139211A5030671518 @default.
- W2058139211 hasAuthorship W2058139211A5046812485 @default.
- W2058139211 hasConcept C11413529 @default.
- W2058139211 hasConcept C120620853 @default.
- W2058139211 hasConcept C138885662 @default.
- W2058139211 hasConcept C154945302 @default.
- W2058139211 hasConcept C159423971 @default.
- W2058139211 hasConcept C202444582 @default.
- W2058139211 hasConcept C2778618852 @default.
- W2058139211 hasConcept C33923547 @default.
- W2058139211 hasConcept C41008148 @default.
- W2058139211 hasConcept C41895202 @default.
- W2058139211 hasConcept C50644808 @default.
- W2058139211 hasConcept C53442348 @default.
- W2058139211 hasConcept C7149132 @default.
- W2058139211 hasConceptScore W2058139211C11413529 @default.
- W2058139211 hasConceptScore W2058139211C120620853 @default.
- W2058139211 hasConceptScore W2058139211C138885662 @default.
- W2058139211 hasConceptScore W2058139211C154945302 @default.
- W2058139211 hasConceptScore W2058139211C159423971 @default.
- W2058139211 hasConceptScore W2058139211C202444582 @default.
- W2058139211 hasConceptScore W2058139211C2778618852 @default.
- W2058139211 hasConceptScore W2058139211C33923547 @default.
- W2058139211 hasConceptScore W2058139211C41008148 @default.
- W2058139211 hasConceptScore W2058139211C41895202 @default.
- W2058139211 hasConceptScore W2058139211C50644808 @default.
- W2058139211 hasConceptScore W2058139211C53442348 @default.
- W2058139211 hasConceptScore W2058139211C7149132 @default.
- W2058139211 hasIssue "5" @default.
- W2058139211 hasLocation W20581392111 @default.
- W2058139211 hasLocation W20581392112 @default.
- W2058139211 hasOpenAccess W2058139211 @default.
- W2058139211 hasPrimaryLocation W20581392111 @default.
- W2058139211 hasRelatedWork W1515407035 @default.
- W2058139211 hasRelatedWork W1991689182 @default.
- W2058139211 hasRelatedWork W2044730254 @default.
- W2058139211 hasRelatedWork W2048442032 @default.
- W2058139211 hasRelatedWork W2112791364 @default.
- W2058139211 hasRelatedWork W2114653151 @default.
- W2058139211 hasRelatedWork W2150103174 @default.
- W2058139211 hasRelatedWork W2380769476 @default.
- W2058139211 hasRelatedWork W4321273133 @default.
- W2058139211 hasRelatedWork W1801289200 @default.
- W2058139211 hasVolume "9" @default.
- W2058139211 isParatext "false" @default.
- W2058139211 isRetracted "false" @default.
- W2058139211 magId "2058139211" @default.
- W2058139211 workType "article" @default.