Matches in SemOpenAlex for { <https://semopenalex.org/work/W2093669436> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2093669436 endingPage "91" @default.
- W2093669436 startingPage "83" @default.
- W2093669436 abstract "Neural networks represent a new approach to artificial intelligence. By using biologically motivated intensively interconnected networks of simple processing elements, certain pattern recognition tasks can be accomplished much faster than with currently used techniques. The most popular means of training these networks is back propagation, a gradient descent technique. The introduction of back propagation revolutionized research in neural networks, but the method has serious drawbacks in training speed and scalability to large problems. This paper compares the use of a general-purpose nonlinear optimizer, GRG2, with back propagation in training neural networks. Parity problems of increasing size are used to evaluate the scalability of each method to larger problems. It was found that GRG2 not only found solutions much faster, but also found much better solutions. The use of nonlinear programming methods in training therefore has the potential to allow neural networks to be applied to problems that have previously been beyond their capabilities." @default.
- W2093669436 created "2016-06-24" @default.
- W2093669436 creator A5013775682 @default.
- W2093669436 creator A5085354839 @default.
- W2093669436 date "1993-08-01" @default.
- W2093669436 modified "2023-09-24" @default.
- W2093669436 title "Training neural networks with the GRG2 nonlinear optimizer" @default.
- W2093669436 cites W125070839 @default.
- W2093669436 cites W1991920230 @default.
- W2093669436 cites W2023810448 @default.
- W2093669436 cites W2024060531 @default.
- W2093669436 cites W2084272399 @default.
- W2093669436 cites W2104670598 @default.
- W2093669436 cites W2130811076 @default.
- W2093669436 cites W4246598646 @default.
- W2093669436 cites W4250621041 @default.
- W2093669436 doi "https://doi.org/10.1016/0377-2217(93)90093-3" @default.
- W2093669436 hasPublicationYear "1993" @default.
- W2093669436 type Work @default.
- W2093669436 sameAs 2093669436 @default.
- W2093669436 citedByCount "30" @default.
- W2093669436 countsByYear W20936694362019 @default.
- W2093669436 countsByYear W20936694362023 @default.
- W2093669436 crossrefType "journal-article" @default.
- W2093669436 hasAuthorship W2093669436A5013775682 @default.
- W2093669436 hasAuthorship W2093669436A5085354839 @default.
- W2093669436 hasConcept C111472728 @default.
- W2093669436 hasConcept C119857082 @default.
- W2093669436 hasConcept C121332964 @default.
- W2093669436 hasConcept C138885662 @default.
- W2093669436 hasConcept C153258448 @default.
- W2093669436 hasConcept C154945302 @default.
- W2093669436 hasConcept C155032097 @default.
- W2093669436 hasConcept C158622935 @default.
- W2093669436 hasConcept C2780586882 @default.
- W2093669436 hasConcept C41008148 @default.
- W2093669436 hasConcept C48044578 @default.
- W2093669436 hasConcept C50644808 @default.
- W2093669436 hasConcept C62520636 @default.
- W2093669436 hasConcept C77088390 @default.
- W2093669436 hasConceptScore W2093669436C111472728 @default.
- W2093669436 hasConceptScore W2093669436C119857082 @default.
- W2093669436 hasConceptScore W2093669436C121332964 @default.
- W2093669436 hasConceptScore W2093669436C138885662 @default.
- W2093669436 hasConceptScore W2093669436C153258448 @default.
- W2093669436 hasConceptScore W2093669436C154945302 @default.
- W2093669436 hasConceptScore W2093669436C155032097 @default.
- W2093669436 hasConceptScore W2093669436C158622935 @default.
- W2093669436 hasConceptScore W2093669436C2780586882 @default.
- W2093669436 hasConceptScore W2093669436C41008148 @default.
- W2093669436 hasConceptScore W2093669436C48044578 @default.
- W2093669436 hasConceptScore W2093669436C50644808 @default.
- W2093669436 hasConceptScore W2093669436C62520636 @default.
- W2093669436 hasConceptScore W2093669436C77088390 @default.
- W2093669436 hasIssue "1" @default.
- W2093669436 hasLocation W20936694361 @default.
- W2093669436 hasOpenAccess W2093669436 @default.
- W2093669436 hasPrimaryLocation W20936694361 @default.
- W2093669436 hasRelatedWork W1183256782 @default.
- W2093669436 hasRelatedWork W1489050811 @default.
- W2093669436 hasRelatedWork W2018863220 @default.
- W2093669436 hasRelatedWork W2093669436 @default.
- W2093669436 hasRelatedWork W2146640810 @default.
- W2093669436 hasRelatedWork W3123071383 @default.
- W2093669436 hasRelatedWork W3159389381 @default.
- W2093669436 hasRelatedWork W3170244987 @default.
- W2093669436 hasRelatedWork W3185486575 @default.
- W2093669436 hasRelatedWork W1629725936 @default.
- W2093669436 hasVolume "69" @default.
- W2093669436 isParatext "false" @default.
- W2093669436 isRetracted "false" @default.
- W2093669436 magId "2093669436" @default.
- W2093669436 workType "article" @default.