Matches in SemOpenAlex for { <https://semopenalex.org/work/W2090975587> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2090975587 endingPage "20" @default.
- W2090975587 startingPage "5" @default.
- W2090975587 abstract "We present a neural network for real-time learning and mapping of patterns using an external performance indicator. In a non-stationary environment where new patterns are introduced over time, the learning process utilises a novel snap-drift algorithm that performs fast, convergent, minimalist learning (snap) when the overall network performance is poor and slower, more cautious learning (drift) when the performance is good. Snap is based on a modified form of Adaptive Resonance Theory (CGIP 37(1987)54); and drift is based on Learning Vector Quantization (LVQ) (Proc. IJCNN 1(1990a)545). The two are combined within a semi-supervised learning system that shifts its learning style whenever it receives a significant change in performance feedback. The learning is capable of rapid re-learning and re-stabilisation, according to changes in external feedback or input patterns. We have incorporated this algorithm into the design of a modular neural network system, Performance-guided Adaptive Resonance Theory (P-ART) (Proc. IJCNN 2(2003)1412; Soft computing systems: Design, Management and application, IOS Press, Netherland, 2002; pp. 21–31). Simulation results show that the system discovers alternative solutions in response to significant changes in the input patterns and/or in the environment, which may require similar patterns to be treated differently over time. The simulations involve attempting to optimise the selection of network services in a non-stationary, real-time active computer network environment, in which the factors influencing the required selections are subject to change." @default.
- W2090975587 created "2016-06-24" @default.
- W2090975587 creator A5000548345 @default.
- W2090975587 creator A5000997645 @default.
- W2090975587 creator A5078442086 @default.
- W2090975587 date "2004-10-01" @default.
- W2090975587 modified "2023-09-25" @default.
- W2090975587 title "Performance-guided neural network for rapidly self-organising active network management" @default.
- W2090975587 cites W134309601 @default.
- W2090975587 cites W1898343769 @default.
- W2090975587 cites W1956244651 @default.
- W2090975587 cites W1967011375 @default.
- W2090975587 cites W1977867644 @default.
- W2090975587 cites W1984226557 @default.
- W2090975587 cites W1987193542 @default.
- W2090975587 cites W1990517717 @default.
- W2090975587 cites W1990863955 @default.
- W2090975587 cites W1991770581 @default.
- W2090975587 cites W2000868189 @default.
- W2090975587 cites W2002329982 @default.
- W2090975587 cites W2012611887 @default.
- W2090975587 cites W2015857587 @default.
- W2090975587 cites W2025200574 @default.
- W2090975587 cites W2034283232 @default.
- W2090975587 cites W2052167102 @default.
- W2090975587 cites W2082979344 @default.
- W2090975587 cites W2106304233 @default.
- W2090975587 cites W2152399141 @default.
- W2090975587 cites W2166280719 @default.
- W2090975587 cites W4242056534 @default.
- W2090975587 cites W4250621041 @default.
- W2090975587 cites W65738273 @default.
- W2090975587 cites W43269207 @default.
- W2090975587 doi "https://doi.org/10.1016/j.neucom.2004.03.001" @default.
- W2090975587 hasPublicationYear "2004" @default.
- W2090975587 type Work @default.
- W2090975587 sameAs 2090975587 @default.
- W2090975587 citedByCount "34" @default.
- W2090975587 countsByYear W20909755872012 @default.
- W2090975587 countsByYear W20909755872013 @default.
- W2090975587 countsByYear W20909755872015 @default.
- W2090975587 countsByYear W20909755872016 @default.
- W2090975587 countsByYear W20909755872022 @default.
- W2090975587 crossrefType "journal-article" @default.
- W2090975587 hasAuthorship W2090975587A5000548345 @default.
- W2090975587 hasAuthorship W2090975587A5000997645 @default.
- W2090975587 hasAuthorship W2090975587A5078442086 @default.
- W2090975587 hasConcept C101468663 @default.
- W2090975587 hasConcept C111919701 @default.
- W2090975587 hasConcept C11413529 @default.
- W2090975587 hasConcept C115755159 @default.
- W2090975587 hasConcept C119857082 @default.
- W2090975587 hasConcept C154945302 @default.
- W2090975587 hasConcept C28855332 @default.
- W2090975587 hasConcept C40567965 @default.
- W2090975587 hasConcept C41008148 @default.
- W2090975587 hasConcept C50644808 @default.
- W2090975587 hasConceptScore W2090975587C101468663 @default.
- W2090975587 hasConceptScore W2090975587C111919701 @default.
- W2090975587 hasConceptScore W2090975587C11413529 @default.
- W2090975587 hasConceptScore W2090975587C115755159 @default.
- W2090975587 hasConceptScore W2090975587C119857082 @default.
- W2090975587 hasConceptScore W2090975587C154945302 @default.
- W2090975587 hasConceptScore W2090975587C28855332 @default.
- W2090975587 hasConceptScore W2090975587C40567965 @default.
- W2090975587 hasConceptScore W2090975587C41008148 @default.
- W2090975587 hasConceptScore W2090975587C50644808 @default.
- W2090975587 hasLocation W20909755871 @default.
- W2090975587 hasOpenAccess W2090975587 @default.
- W2090975587 hasPrimaryLocation W20909755871 @default.
- W2090975587 hasRelatedWork W2009688482 @default.
- W2090975587 hasRelatedWork W2025883075 @default.
- W2090975587 hasRelatedWork W2348528394 @default.
- W2090975587 hasRelatedWork W2692154213 @default.
- W2090975587 hasRelatedWork W2893268702 @default.
- W2090975587 hasRelatedWork W2961085424 @default.
- W2090975587 hasRelatedWork W2996077742 @default.
- W2090975587 hasRelatedWork W3167352788 @default.
- W2090975587 hasRelatedWork W4306674287 @default.
- W2090975587 hasRelatedWork W1629725936 @default.
- W2090975587 hasVolume "61" @default.
- W2090975587 isParatext "false" @default.
- W2090975587 isRetracted "false" @default.
- W2090975587 magId "2090975587" @default.
- W2090975587 workType "article" @default.