Matches in SemOpenAlex for { <https://semopenalex.org/work/W1584706890> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W1584706890 abstract "Traditional neural network training techniques do not work well on problems with many discontinuities, such as those that arise in multicomputer communication cost modeling. We develop a new algorithm to solve this problem. This algorithm incrementally adds modules to the network, successively expanding the 'window' in the data space where the current module works well. The need for a new module is automatically recognized by the system. This algorithm performs very well on problems with many discontinuities, and requires fewer computations than traditional backpropagation. >" @default.
- W1584706890 created "2016-06-24" @default.
- W1584706890 creator A5000736939 @default.
- W1584706890 creator A5051923415 @default.
- W1584706890 creator A5074787525 @default.
- W1584706890 creator A5077570468 @default.
- W1584706890 date "2002-12-17" @default.
- W1584706890 modified "2023-09-25" @default.
- W1584706890 title "An incremental network construction algorithm for approximating discontinuous functions" @default.
- W1584706890 cites W1580138380 @default.
- W1584706890 cites W1971735090 @default.
- W1584706890 cites W2022231604 @default.
- W1584706890 cites W2103496339 @default.
- W1584706890 cites W2109779438 @default.
- W1584706890 cites W2116143466 @default.
- W1584706890 cites W2143956139 @default.
- W1584706890 cites W2149846618 @default.
- W1584706890 cites W2151843700 @default.
- W1584706890 cites W3146803896 @default.
- W1584706890 doi "https://doi.org/10.1109/icnn.1994.374556" @default.
- W1584706890 hasPublicationYear "2002" @default.
- W1584706890 type Work @default.
- W1584706890 sameAs 1584706890 @default.
- W1584706890 citedByCount "1" @default.
- W1584706890 crossrefType "proceedings-article" @default.
- W1584706890 hasAuthorship W1584706890A5000736939 @default.
- W1584706890 hasAuthorship W1584706890A5051923415 @default.
- W1584706890 hasAuthorship W1584706890A5074787525 @default.
- W1584706890 hasAuthorship W1584706890A5077570468 @default.
- W1584706890 hasConcept C11413529 @default.
- W1584706890 hasConcept C134306372 @default.
- W1584706890 hasConcept C154945302 @default.
- W1584706890 hasConcept C155032097 @default.
- W1584706890 hasConcept C15627037 @default.
- W1584706890 hasConcept C33923547 @default.
- W1584706890 hasConcept C41008148 @default.
- W1584706890 hasConcept C45374587 @default.
- W1584706890 hasConcept C50644808 @default.
- W1584706890 hasConceptScore W1584706890C11413529 @default.
- W1584706890 hasConceptScore W1584706890C134306372 @default.
- W1584706890 hasConceptScore W1584706890C154945302 @default.
- W1584706890 hasConceptScore W1584706890C155032097 @default.
- W1584706890 hasConceptScore W1584706890C15627037 @default.
- W1584706890 hasConceptScore W1584706890C33923547 @default.
- W1584706890 hasConceptScore W1584706890C41008148 @default.
- W1584706890 hasConceptScore W1584706890C45374587 @default.
- W1584706890 hasConceptScore W1584706890C50644808 @default.
- W1584706890 hasLocation W15847068901 @default.
- W1584706890 hasOpenAccess W1584706890 @default.
- W1584706890 hasPrimaryLocation W15847068901 @default.
- W1584706890 hasRelatedWork W2003465964 @default.
- W1584706890 hasRelatedWork W2057623054 @default.
- W1584706890 hasRelatedWork W2317200988 @default.
- W1584706890 hasRelatedWork W2358668433 @default.
- W1584706890 hasRelatedWork W2371447506 @default.
- W1584706890 hasRelatedWork W2376932109 @default.
- W1584706890 hasRelatedWork W2386767533 @default.
- W1584706890 hasRelatedWork W2390279801 @default.
- W1584706890 hasRelatedWork W2748952813 @default.
- W1584706890 hasRelatedWork W2899084033 @default.
- W1584706890 isParatext "false" @default.
- W1584706890 isRetracted "false" @default.
- W1584706890 magId "1584706890" @default.
- W1584706890 workType "article" @default.