Matches in SemOpenAlex for { <https://semopenalex.org/work/W2482510314> ?p ?o ?g. }
Showing items 1 to 46 of
46
with 100 items per page.
- W2482510314 endingPage "147" @default.
- W2482510314 startingPage "127" @default.
- W2482510314 abstract "The fundamental property of feedforward neural networks parsimonious approximation makes them excellent candidates for modeling static nonlinear processes from measured data. Similarly, feedback (or recurrent) neural networks have very attractive properties for the dynamic nonlinear modeling of artificial or natural processes; however, the design of such networks is more complex than that of feedforward neural nets, because the designer has additional degrees of freedom. In the present paper, we show that this complexity may be greatly reduced by (i) incorporating into the very structure of the network all the available mathematical knowledge about the process to be modeled, and by (ii) transforming the resulting network into a universal form, termed canonical form, which further reduces the complexity of analyzing and training dynamic neural models." @default.
- W2482510314 created "2016-08-23" @default.
- W2482510314 creator A5034139703 @default.
- W2482510314 date "1999-05-01" @default.
- W2482510314 modified "2023-09-23" @default.
- W2482510314 title "REDUCING THE COMPLEXITY OF NEURAL NETS FOR INDUSTRIAL APPLICATIONS AND BIOLOGICAL MODELS" @default.
- W2482510314 cites W1554663460 @default.
- W2482510314 cites W2058538513 @default.
- W2482510314 cites W2127063611 @default.
- W2482510314 cites W2480616039 @default.
- W2482510314 cites W2515831704 @default.
- W2482510314 cites W3022974090 @default.
- W2482510314 doi "https://doi.org/10.1142/9789812818041_0006" @default.
- W2482510314 hasPublicationYear "1999" @default.
- W2482510314 type Work @default.
- W2482510314 sameAs 2482510314 @default.
- W2482510314 citedByCount "0" @default.
- W2482510314 crossrefType "book-chapter" @default.
- W2482510314 hasAuthorship W2482510314A5034139703 @default.
- W2482510314 hasBestOaLocation W24825103142 @default.
- W2482510314 hasConcept C127413603 @default.
- W2482510314 hasConcept C183696295 @default.
- W2482510314 hasConcept C41008148 @default.
- W2482510314 hasConceptScore W2482510314C127413603 @default.
- W2482510314 hasConceptScore W2482510314C183696295 @default.
- W2482510314 hasConceptScore W2482510314C41008148 @default.
- W2482510314 hasLocation W24825103141 @default.
- W2482510314 hasLocation W24825103142 @default.
- W2482510314 hasOpenAccess W2482510314 @default.
- W2482510314 hasPrimaryLocation W24825103141 @default.
- W2482510314 hasRelatedWork W2096946506 @default.
- W2482510314 hasRelatedWork W2130043461 @default.
- W2482510314 hasRelatedWork W2350741829 @default.
- W2482510314 hasRelatedWork W2358668433 @default.
- W2482510314 hasRelatedWork W2376932109 @default.
- W2482510314 hasRelatedWork W2382290278 @default.
- W2482510314 hasRelatedWork W2390279801 @default.
- W2482510314 hasRelatedWork W2748952813 @default.
- W2482510314 hasRelatedWork W2899084033 @default.
- W2482510314 hasRelatedWork W3004735627 @default.
- W2482510314 isParatext "false" @default.
- W2482510314 isRetracted "false" @default.
- W2482510314 magId "2482510314" @default.
- W2482510314 workType "book-chapter" @default.