Matches in SemOpenAlex for { <https://semopenalex.org/work/W2242785489> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2242785489 endingPage "55" @default.
- W2242785489 startingPage "51" @default.
- W2242785489 abstract "A discussion on the representational abilities of single layer recurrent neural networks (SLRNNs) is presented. The fact that SLRNNs can not implement all finite-state recognizers is addressed. However, there are methods that can be used to expand the representational abilities of SLRNNs, and some of these are explained. The authors call such systems augmented SLRNNs. Some possibilities for augmented SLRNNs are: adding a layer of feedforward neurons to the SLRNN, allowing the SLRNN to have an extra time step to calculate the solution, and increasing the order of the SLRNN. It is significant that, for some problems, some augmented SLRNNs must actually implement a non-minimal finite-state recognizer that is equivalent to the desired finite-state recognizer. Simulations are performed that demonstrate the use of both a SLRNN and an augmented SLRNN for the problem of learning an odd parity finite-state recognizer using a gradient descent method." @default.
- W2242785489 created "2016-06-24" @default.
- W2242785489 creator A5001294898 @default.
- W2242785489 creator A5047650583 @default.
- W2242785489 date "1993-05-25" @default.
- W2242785489 modified "2023-09-28" @default.
- W2242785489 title "On recurrent neural networks and representing finite-state recognizers" @default.
- W2242785489 hasPublicationYear "1993" @default.
- W2242785489 type Work @default.
- W2242785489 sameAs 2242785489 @default.
- W2242785489 citedByCount "2" @default.
- W2242785489 crossrefType "journal-article" @default.
- W2242785489 hasAuthorship W2242785489A5001294898 @default.
- W2242785489 hasAuthorship W2242785489A5047650583 @default.
- W2242785489 hasConcept C11413529 @default.
- W2242785489 hasConcept C119857082 @default.
- W2242785489 hasConcept C127413603 @default.
- W2242785489 hasConcept C133731056 @default.
- W2242785489 hasConcept C147168706 @default.
- W2242785489 hasConcept C153258448 @default.
- W2242785489 hasConcept C154945302 @default.
- W2242785489 hasConcept C178790620 @default.
- W2242785489 hasConcept C185592680 @default.
- W2242785489 hasConcept C2779227376 @default.
- W2242785489 hasConcept C28490314 @default.
- W2242785489 hasConcept C2983497884 @default.
- W2242785489 hasConcept C38858127 @default.
- W2242785489 hasConcept C41008148 @default.
- W2242785489 hasConcept C47702885 @default.
- W2242785489 hasConcept C48103436 @default.
- W2242785489 hasConcept C50644808 @default.
- W2242785489 hasConcept C80444323 @default.
- W2242785489 hasConcept C98763669 @default.
- W2242785489 hasConceptScore W2242785489C11413529 @default.
- W2242785489 hasConceptScore W2242785489C119857082 @default.
- W2242785489 hasConceptScore W2242785489C127413603 @default.
- W2242785489 hasConceptScore W2242785489C133731056 @default.
- W2242785489 hasConceptScore W2242785489C147168706 @default.
- W2242785489 hasConceptScore W2242785489C153258448 @default.
- W2242785489 hasConceptScore W2242785489C154945302 @default.
- W2242785489 hasConceptScore W2242785489C178790620 @default.
- W2242785489 hasConceptScore W2242785489C185592680 @default.
- W2242785489 hasConceptScore W2242785489C2779227376 @default.
- W2242785489 hasConceptScore W2242785489C28490314 @default.
- W2242785489 hasConceptScore W2242785489C2983497884 @default.
- W2242785489 hasConceptScore W2242785489C38858127 @default.
- W2242785489 hasConceptScore W2242785489C41008148 @default.
- W2242785489 hasConceptScore W2242785489C47702885 @default.
- W2242785489 hasConceptScore W2242785489C48103436 @default.
- W2242785489 hasConceptScore W2242785489C50644808 @default.
- W2242785489 hasConceptScore W2242785489C80444323 @default.
- W2242785489 hasConceptScore W2242785489C98763669 @default.
- W2242785489 hasLocation W22427854891 @default.
- W2242785489 hasOpenAccess W2242785489 @default.
- W2242785489 hasPrimaryLocation W22427854891 @default.
- W2242785489 hasRelatedWork W1497566878 @default.
- W2242785489 hasRelatedWork W1506693879 @default.
- W2242785489 hasRelatedWork W1529554624 @default.
- W2242785489 hasRelatedWork W1538606284 @default.
- W2242785489 hasRelatedWork W1553905320 @default.
- W2242785489 hasRelatedWork W1559792554 @default.
- W2242785489 hasRelatedWork W1563120954 @default.
- W2242785489 hasRelatedWork W1653372627 @default.
- W2242785489 hasRelatedWork W1824158299 @default.
- W2242785489 hasRelatedWork W2084527119 @default.
- W2242785489 hasRelatedWork W2100311509 @default.
- W2242785489 hasRelatedWork W2126900244 @default.
- W2242785489 hasRelatedWork W2127467909 @default.
- W2242785489 hasRelatedWork W2139276599 @default.
- W2242785489 hasRelatedWork W2141420161 @default.
- W2242785489 hasRelatedWork W2144196999 @default.
- W2242785489 hasRelatedWork W2146758552 @default.
- W2242785489 hasRelatedWork W2155497161 @default.
- W2242785489 hasRelatedWork W2122882161 @default.
- W2242785489 hasRelatedWork W2151221590 @default.
- W2242785489 isParatext "false" @default.
- W2242785489 isRetracted "false" @default.
- W2242785489 magId "2242785489" @default.
- W2242785489 workType "article" @default.