Matches in SemOpenAlex for { <https://semopenalex.org/work/W2024652935> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2024652935 abstract "Application of neural networks to problems with a large number of sensory inputs is severely limited when the processing elements (PEs) need to be fully connected. This paper presents a new network model in which a trade off between the number of connections to a node and the number of processing layers can be made. This trade off is an important issue in the VLSI implementation of neural networks. The performance and capability of a hierarchical pyramidal network architecture of limited fan-in PE layers is analyzed. Analysis of this architecture requires the development of a new learning rule, since each PE has access to limited information about the entire network input. A spatially local unsupervised training rule is developed in which each PE optimizes the fraction of its output variance contributed by input correlations, resulting in PEs behaving as adaptive local correlation detectors. It is also shown that the output of a PE optimally represents the mutual information among the inputs to that PE. Applications of the developed model in image compression and motion detection are presented.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only." @default.
- W2024652935 created "2016-06-24" @default.
- W2024652935 creator A5060484436 @default.
- W2024652935 date "1992-07-01" @default.
- W2024652935 modified "2023-09-27" @default.
- W2024652935 title "<title>Uniformly sparse neural networks</title>" @default.
- W2024652935 doi "https://doi.org/10.1117/12.140147" @default.
- W2024652935 hasPublicationYear "1992" @default.
- W2024652935 type Work @default.
- W2024652935 sameAs 2024652935 @default.
- W2024652935 citedByCount "0" @default.
- W2024652935 crossrefType "proceedings-article" @default.
- W2024652935 hasAuthorship W2024652935A5060484436 @default.
- W2024652935 hasConcept C111919701 @default.
- W2024652935 hasConcept C113775141 @default.
- W2024652935 hasConcept C120665830 @default.
- W2024652935 hasConcept C121332964 @default.
- W2024652935 hasConcept C127413603 @default.
- W2024652935 hasConcept C14580979 @default.
- W2024652935 hasConcept C149635348 @default.
- W2024652935 hasConcept C151857401 @default.
- W2024652935 hasConcept C153180895 @default.
- W2024652935 hasConcept C154945302 @default.
- W2024652935 hasConcept C193415008 @default.
- W2024652935 hasConcept C2779127903 @default.
- W2024652935 hasConcept C31258907 @default.
- W2024652935 hasConcept C41008148 @default.
- W2024652935 hasConcept C50644808 @default.
- W2024652935 hasConcept C62611344 @default.
- W2024652935 hasConcept C66938386 @default.
- W2024652935 hasConcept C71901391 @default.
- W2024652935 hasConceptScore W2024652935C111919701 @default.
- W2024652935 hasConceptScore W2024652935C113775141 @default.
- W2024652935 hasConceptScore W2024652935C120665830 @default.
- W2024652935 hasConceptScore W2024652935C121332964 @default.
- W2024652935 hasConceptScore W2024652935C127413603 @default.
- W2024652935 hasConceptScore W2024652935C14580979 @default.
- W2024652935 hasConceptScore W2024652935C149635348 @default.
- W2024652935 hasConceptScore W2024652935C151857401 @default.
- W2024652935 hasConceptScore W2024652935C153180895 @default.
- W2024652935 hasConceptScore W2024652935C154945302 @default.
- W2024652935 hasConceptScore W2024652935C193415008 @default.
- W2024652935 hasConceptScore W2024652935C2779127903 @default.
- W2024652935 hasConceptScore W2024652935C31258907 @default.
- W2024652935 hasConceptScore W2024652935C41008148 @default.
- W2024652935 hasConceptScore W2024652935C50644808 @default.
- W2024652935 hasConceptScore W2024652935C62611344 @default.
- W2024652935 hasConceptScore W2024652935C66938386 @default.
- W2024652935 hasConceptScore W2024652935C71901391 @default.
- W2024652935 hasLocation W20246529351 @default.
- W2024652935 hasOpenAccess W2024652935 @default.
- W2024652935 hasPrimaryLocation W20246529351 @default.
- W2024652935 hasRelatedWork W1523290505 @default.
- W2024652935 hasRelatedWork W1823654389 @default.
- W2024652935 hasRelatedWork W1970686249 @default.
- W2024652935 hasRelatedWork W2011673440 @default.
- W2024652935 hasRelatedWork W2016300089 @default.
- W2024652935 hasRelatedWork W2085961337 @default.
- W2024652935 hasRelatedWork W2088549260 @default.
- W2024652935 hasRelatedWork W2123291128 @default.
- W2024652935 hasRelatedWork W2128515462 @default.
- W2024652935 hasRelatedWork W2148228664 @default.
- W2024652935 hasRelatedWork W2361650588 @default.
- W2024652935 hasRelatedWork W2612199584 @default.
- W2024652935 hasRelatedWork W2748257183 @default.
- W2024652935 hasRelatedWork W3003652842 @default.
- W2024652935 hasRelatedWork W3122138730 @default.
- W2024652935 hasRelatedWork W93911711 @default.
- W2024652935 hasRelatedWork W2119832825 @default.
- W2024652935 hasRelatedWork W2185467021 @default.
- W2024652935 hasRelatedWork W2872946738 @default.
- W2024652935 hasRelatedWork W3001949738 @default.
- W2024652935 isParatext "false" @default.
- W2024652935 isRetracted "false" @default.
- W2024652935 magId "2024652935" @default.
- W2024652935 workType "article" @default.