Matches in SemOpenAlex for { <https://semopenalex.org/work/W2111053603> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2111053603 endingPage "283" @default.
- W2111053603 startingPage "272" @default.
- W2111053603 abstract "Conventional neural nets perform functional mappings from their input space to their output space in a manner analogous to long-term biological memory. This paper presents a method of designing neural nets where recurrent signal loops store knowledge in a manner analogous to short-term memory. The synaptic weights encode a learning algorithm. This gives these nets the ability to dynamically learn any functional mapping from a (possibly very large) set, without changing any synaptic weight. These nets are adaptive dynamic systems. Learning is online continually taking place as part of the net's overall behavior instead of a separate, externally driven process. We present four high-order fixed-weight learning nets. Two of these have standard backpropagation embedded in their synaptic weights. The other two utilize a more efficient gradient-descent-based rule. This scheme was discovered by examining variations in fixed-weight topology. We present empirical tests showing that all these nets could successfully learn functions from both discrete (Boolean) and continuous function sets. Largely, the networks were robust with respect to perturbations in the synaptic weights. The exception was the recurrent connections used to store information. These required a tight tolerance of 0.5%. The cost of these nets scaled approximately in proportion to the total number of synapses. We consider evolving fixed weight networks tailored to a specific problem class by analyzing the meta-learning cost surface of the networks presented." @default.
- W2111053603 created "2016-06-24" @default.
- W2111053603 creator A5003418617 @default.
- W2111053603 creator A5038008558 @default.
- W2111053603 creator A5073049945 @default.
- W2111053603 date "1999-03-01" @default.
- W2111053603 modified "2023-09-26" @default.
- W2111053603 title "Fixed-weight on-line learning" @default.
- W2111053603 cites W1979103773 @default.
- W2111053603 cites W1980411262 @default.
- W2111053603 cites W1994405449 @default.
- W2111053603 cites W1995341919 @default.
- W2111053603 cites W2007431958 @default.
- W2111053603 cites W2016589492 @default.
- W2111053603 cites W2025905137 @default.
- W2111053603 cites W2037527891 @default.
- W2111053603 cites W2053608765 @default.
- W2111053603 cites W2079596080 @default.
- W2111053603 cites W2129353152 @default.
- W2111053603 cites W2163181514 @default.
- W2111053603 cites W2281866017 @default.
- W2111053603 doi "https://doi.org/10.1109/72.750553" @default.
- W2111053603 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/18252526" @default.
- W2111053603 hasPublicationYear "1999" @default.
- W2111053603 type Work @default.
- W2111053603 sameAs 2111053603 @default.
- W2111053603 citedByCount "37" @default.
- W2111053603 countsByYear W21110536032013 @default.
- W2111053603 countsByYear W21110536032014 @default.
- W2111053603 countsByYear W21110536032016 @default.
- W2111053603 countsByYear W21110536032017 @default.
- W2111053603 countsByYear W21110536032018 @default.
- W2111053603 countsByYear W21110536032019 @default.
- W2111053603 countsByYear W21110536032020 @default.
- W2111053603 countsByYear W21110536032021 @default.
- W2111053603 countsByYear W21110536032022 @default.
- W2111053603 countsByYear W21110536032023 @default.
- W2111053603 crossrefType "journal-article" @default.
- W2111053603 hasAuthorship W2111053603A5003418617 @default.
- W2111053603 hasAuthorship W2111053603A5038008558 @default.
- W2111053603 hasAuthorship W2111053603A5073049945 @default.
- W2111053603 hasConcept C104317684 @default.
- W2111053603 hasConcept C11413529 @default.
- W2111053603 hasConcept C120822770 @default.
- W2111053603 hasConcept C14036430 @default.
- W2111053603 hasConcept C153258448 @default.
- W2111053603 hasConcept C154945302 @default.
- W2111053603 hasConcept C155032097 @default.
- W2111053603 hasConcept C185592680 @default.
- W2111053603 hasConcept C187455244 @default.
- W2111053603 hasConcept C2779127903 @default.
- W2111053603 hasConcept C41008148 @default.
- W2111053603 hasConcept C50644808 @default.
- W2111053603 hasConcept C55493867 @default.
- W2111053603 hasConcept C66746571 @default.
- W2111053603 hasConcept C66949984 @default.
- W2111053603 hasConcept C78458016 @default.
- W2111053603 hasConcept C80444323 @default.
- W2111053603 hasConcept C86803240 @default.
- W2111053603 hasConceptScore W2111053603C104317684 @default.
- W2111053603 hasConceptScore W2111053603C11413529 @default.
- W2111053603 hasConceptScore W2111053603C120822770 @default.
- W2111053603 hasConceptScore W2111053603C14036430 @default.
- W2111053603 hasConceptScore W2111053603C153258448 @default.
- W2111053603 hasConceptScore W2111053603C154945302 @default.
- W2111053603 hasConceptScore W2111053603C155032097 @default.
- W2111053603 hasConceptScore W2111053603C185592680 @default.
- W2111053603 hasConceptScore W2111053603C187455244 @default.
- W2111053603 hasConceptScore W2111053603C2779127903 @default.
- W2111053603 hasConceptScore W2111053603C41008148 @default.
- W2111053603 hasConceptScore W2111053603C50644808 @default.
- W2111053603 hasConceptScore W2111053603C55493867 @default.
- W2111053603 hasConceptScore W2111053603C66746571 @default.
- W2111053603 hasConceptScore W2111053603C66949984 @default.
- W2111053603 hasConceptScore W2111053603C78458016 @default.
- W2111053603 hasConceptScore W2111053603C80444323 @default.
- W2111053603 hasConceptScore W2111053603C86803240 @default.
- W2111053603 hasIssue "2" @default.
- W2111053603 hasLocation W21110536031 @default.
- W2111053603 hasLocation W21110536032 @default.
- W2111053603 hasOpenAccess W2111053603 @default.
- W2111053603 hasPrimaryLocation W21110536031 @default.
- W2111053603 hasRelatedWork W1969426462 @default.
- W2111053603 hasRelatedWork W1983738889 @default.
- W2111053603 hasRelatedWork W2111053603 @default.
- W2111053603 hasRelatedWork W2534287762 @default.
- W2111053603 hasRelatedWork W2952934527 @default.
- W2111053603 hasRelatedWork W3123071383 @default.
- W2111053603 hasRelatedWork W3159389381 @default.
- W2111053603 hasRelatedWork W3170244987 @default.
- W2111053603 hasRelatedWork W4300839022 @default.
- W2111053603 hasRelatedWork W4323913440 @default.
- W2111053603 hasVolume "10" @default.
- W2111053603 isParatext "false" @default.
- W2111053603 isRetracted "false" @default.
- W2111053603 magId "2111053603" @default.
- W2111053603 workType "article" @default.