Matches in SemOpenAlex for { <https://semopenalex.org/work/W1567809998> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W1567809998 endingPage "166" @default.
- W1567809998 startingPage "158" @default.
- W1567809998 abstract "In this paper, we explore the parallel implementation of the backpropagation algorithm with and without hidden layers on MasPar MP-1. This implementation is based on a SIMD architecture, and uses a backpropagation model. Our implementation uses weight batching versus on-line updating of the weights which is used by most serial and parallel implementations of backpropagation. This method results in a smoother convergence to a solution which is comparable to that of the popular method. Versus various systolic array implementations of the backpropagation algorithm which are data driven, and exploit pipelined parallelism, we have developed a true SIMD algorithm which is control driven and exploits two types of parallelism inherent in backpropagation feedforward, layered neural networks, namely architectural parallelism and data parallelism. Most importantly, the processing time is reduced both theoretically and experimentally by the order of 3000 for a network with 7-100-10 input-hidden-output neurons and 1188 training. With this algorithm we have achieved speeds of up to 70 Million Connections per Second (MCS) as throughput of a network stage and over 180 Million Connection UPdates per Second (MCUPS) for training the above network. This is the fastest performance of the standard backpropagation algorithm reported to date." @default.
- W1567809998 created "2016-06-24" @default.
- W1567809998 creator A5042304681 @default.
- W1567809998 creator A5083478920 @default.
- W1567809998 date "1993-01-01" @default.
- W1567809998 modified "2023-09-23" @default.
- W1567809998 title "A PARALLEL IMPLEMENTATION OF BACKPROPAGATION NEURAL NETWORK ON MASPAR MP-1" @default.
- W1567809998 cites W100003592 @default.
- W1567809998 cites W1492242795 @default.
- W1567809998 cites W1520460310 @default.
- W1567809998 cites W1945445380 @default.
- W1567809998 cites W1979707012 @default.
- W1567809998 cites W199739722 @default.
- W1567809998 cites W2017356132 @default.
- W1567809998 cites W2119241866 @default.
- W1567809998 cites W2138711634 @default.
- W1567809998 cites W2168866303 @default.
- W1567809998 cites W2266946488 @default.
- W1567809998 cites W2498441527 @default.
- W1567809998 cites W2541168412 @default.
- W1567809998 cites W3036784799 @default.
- W1567809998 cites W3150413596 @default.
- W1567809998 hasPublicationYear "1993" @default.
- W1567809998 type Work @default.
- W1567809998 sameAs 1567809998 @default.
- W1567809998 citedByCount "2" @default.
- W1567809998 crossrefType "proceedings-article" @default.
- W1567809998 hasAuthorship W1567809998A5042304681 @default.
- W1567809998 hasAuthorship W1567809998A5083478920 @default.
- W1567809998 hasConcept C106515295 @default.
- W1567809998 hasConcept C11413529 @default.
- W1567809998 hasConcept C150552126 @default.
- W1567809998 hasConcept C154945302 @default.
- W1567809998 hasConcept C155032097 @default.
- W1567809998 hasConcept C162324750 @default.
- W1567809998 hasConcept C165696696 @default.
- W1567809998 hasConcept C173608175 @default.
- W1567809998 hasConcept C2777303404 @default.
- W1567809998 hasConcept C2781172179 @default.
- W1567809998 hasConcept C38652104 @default.
- W1567809998 hasConcept C41008148 @default.
- W1567809998 hasConcept C42992933 @default.
- W1567809998 hasConcept C47702885 @default.
- W1567809998 hasConcept C50522688 @default.
- W1567809998 hasConcept C50644808 @default.
- W1567809998 hasConcept C61483411 @default.
- W1567809998 hasConceptScore W1567809998C106515295 @default.
- W1567809998 hasConceptScore W1567809998C11413529 @default.
- W1567809998 hasConceptScore W1567809998C150552126 @default.
- W1567809998 hasConceptScore W1567809998C154945302 @default.
- W1567809998 hasConceptScore W1567809998C155032097 @default.
- W1567809998 hasConceptScore W1567809998C162324750 @default.
- W1567809998 hasConceptScore W1567809998C165696696 @default.
- W1567809998 hasConceptScore W1567809998C173608175 @default.
- W1567809998 hasConceptScore W1567809998C2777303404 @default.
- W1567809998 hasConceptScore W1567809998C2781172179 @default.
- W1567809998 hasConceptScore W1567809998C38652104 @default.
- W1567809998 hasConceptScore W1567809998C41008148 @default.
- W1567809998 hasConceptScore W1567809998C42992933 @default.
- W1567809998 hasConceptScore W1567809998C47702885 @default.
- W1567809998 hasConceptScore W1567809998C50522688 @default.
- W1567809998 hasConceptScore W1567809998C50644808 @default.
- W1567809998 hasConceptScore W1567809998C61483411 @default.
- W1567809998 hasLocation W15678099981 @default.
- W1567809998 hasOpenAccess W1567809998 @default.
- W1567809998 hasPrimaryLocation W15678099981 @default.
- W1567809998 hasRelatedWork W1540083187 @default.
- W1567809998 hasRelatedWork W1927798802 @default.
- W1567809998 hasRelatedWork W1966484415 @default.
- W1567809998 hasRelatedWork W1971593477 @default.
- W1567809998 hasRelatedWork W2030656367 @default.
- W1567809998 hasRelatedWork W2122297221 @default.
- W1567809998 hasRelatedWork W2320437766 @default.
- W1567809998 hasRelatedWork W237402371 @default.
- W1567809998 hasRelatedWork W2436190281 @default.
- W1567809998 hasRelatedWork W2497655912 @default.
- W1567809998 hasRelatedWork W2553659055 @default.
- W1567809998 hasRelatedWork W2618439228 @default.
- W1567809998 hasRelatedWork W2742924380 @default.
- W1567809998 hasRelatedWork W2889465699 @default.
- W1567809998 hasRelatedWork W297527462 @default.
- W1567809998 hasRelatedWork W2981638121 @default.
- W1567809998 hasRelatedWork W3010259307 @default.
- W1567809998 hasRelatedWork W3106955873 @default.
- W1567809998 hasRelatedWork W3204939319 @default.
- W1567809998 hasRelatedWork W194209700 @default.
- W1567809998 isParatext "false" @default.
- W1567809998 isRetracted "false" @default.
- W1567809998 magId "1567809998" @default.
- W1567809998 workType "article" @default.