Matches in SemOpenAlex for { <https://semopenalex.org/work/W2221267766> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2221267766 abstract "Neural associative memories have been extensively used in applications that perform classification or some kind of input-output mapping. The main advantage of neural associative memories over conventional computer memories is their robustness in noisy environments, generalization and fast retrieval capabilities. In this work we use a robust associative memory model to investigate the performance, capacity and saturation effects of three of the most popular associative memory paradigms, namely: back-propagation networks, correlation matrix memories and generalized inverse memories. The comparison studies use binary character recognition and spelling correction as application domains. Our analytic and experimental modeling shows that correlation matrix memories used as classifiers exhibit overall superiority over other training rules. The correlation matrix memories are then used as the building block of a new neural model for semantic categorization and concept formation. The proposed model represents a hierarchical two-level associative memory, where the first level memory stores categories (concepts) of semantically related items, and each of the second level memories stores items (prototypes) forming a given concept. Memory construction (or learning) is based on supervised learning. Besides its ability to form and store semantic categories of input patterns, the proposed hierarchical model offers substantial scaling advantages over traditional single-level associative memory systems in terms of software implementations. Experimental results (assuming fixed prototypes) for binary character recognition and spelling correction applications demonstrate excellent quality of associative retrieval and superior scaling properties of the proposed model. Finally, we propose an iterative scheme for adaptive prototype formation from repeated presentations of noisy inputs, and present theoretical analysis and proof of convergence. We also find optimal adaptation parameters that provide the best convergence rate." @default.
- W2221267766 created "2016-06-24" @default.
- W2221267766 creator A5000218914 @default.
- W2221267766 creator A5051555620 @default.
- W2221267766 date "1990-01-01" @default.
- W2221267766 modified "2023-09-23" @default.
- W2221267766 title "Performance of neural associative memories for character recognition and associative database retrieval" @default.
- W2221267766 hasPublicationYear "1990" @default.
- W2221267766 type Work @default.
- W2221267766 sameAs 2221267766 @default.
- W2221267766 citedByCount "0" @default.
- W2221267766 crossrefType "journal-article" @default.
- W2221267766 hasAuthorship W2221267766A5000218914 @default.
- W2221267766 hasAuthorship W2221267766A5051555620 @default.
- W2221267766 hasConcept C120620853 @default.
- W2221267766 hasConcept C154945302 @default.
- W2221267766 hasConcept C159423971 @default.
- W2221267766 hasConcept C163561899 @default.
- W2221267766 hasConcept C178790620 @default.
- W2221267766 hasConcept C185592680 @default.
- W2221267766 hasConcept C202444582 @default.
- W2221267766 hasConcept C2781311116 @default.
- W2221267766 hasConcept C33923547 @default.
- W2221267766 hasConcept C41008148 @default.
- W2221267766 hasConcept C50644808 @default.
- W2221267766 hasConcept C53442348 @default.
- W2221267766 hasConceptScore W2221267766C120620853 @default.
- W2221267766 hasConceptScore W2221267766C154945302 @default.
- W2221267766 hasConceptScore W2221267766C159423971 @default.
- W2221267766 hasConceptScore W2221267766C163561899 @default.
- W2221267766 hasConceptScore W2221267766C178790620 @default.
- W2221267766 hasConceptScore W2221267766C185592680 @default.
- W2221267766 hasConceptScore W2221267766C202444582 @default.
- W2221267766 hasConceptScore W2221267766C2781311116 @default.
- W2221267766 hasConceptScore W2221267766C33923547 @default.
- W2221267766 hasConceptScore W2221267766C41008148 @default.
- W2221267766 hasConceptScore W2221267766C50644808 @default.
- W2221267766 hasConceptScore W2221267766C53442348 @default.
- W2221267766 hasLocation W22212677661 @default.
- W2221267766 hasOpenAccess W2221267766 @default.
- W2221267766 hasPrimaryLocation W22212677661 @default.
- W2221267766 hasRelatedWork W1968017374 @default.
- W2221267766 hasRelatedWork W1980026108 @default.
- W2221267766 hasRelatedWork W1991848143 @default.
- W2221267766 hasRelatedWork W1998200334 @default.
- W2221267766 hasRelatedWork W2024773309 @default.
- W2221267766 hasRelatedWork W2049322669 @default.
- W2221267766 hasRelatedWork W2068574914 @default.
- W2221267766 hasRelatedWork W2107898491 @default.
- W2221267766 hasRelatedWork W2128436809 @default.
- W2221267766 hasRelatedWork W2154769732 @default.
- W2221267766 hasRelatedWork W2226165662 @default.
- W2221267766 hasRelatedWork W2362300612 @default.
- W2221267766 hasRelatedWork W2379570313 @default.
- W2221267766 hasRelatedWork W2463695692 @default.
- W2221267766 hasRelatedWork W2551597274 @default.
- W2221267766 hasRelatedWork W2617166445 @default.
- W2221267766 hasRelatedWork W2741329592 @default.
- W2221267766 hasRelatedWork W279701215 @default.
- W2221267766 hasRelatedWork W3201359912 @default.
- W2221267766 hasRelatedWork W3203335147 @default.
- W2221267766 isParatext "false" @default.
- W2221267766 isRetracted "false" @default.
- W2221267766 magId "2221267766" @default.
- W2221267766 workType "article" @default.