Matches in SemOpenAlex for { <https://semopenalex.org/work/W2038388994> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2038388994 abstract "Neural network minimization is a process in which non-affecting elements (non-contributing processing elements and weights) are deleted. This results in the network with a minimum configuration and positively contributing elements. In general, the scope of the minimization process is to achieve a network which provides optimal solution for a given task without loss of performance. Therefore, study into network minimization becomes essential for complicated tasks. The present study investigates ways of developing automatic thresholding methods for weight deleting process to minimize the network resulting in enhanced performances for classification of six control chart patterns. To achieve this aim, two weight deleting processes are developed including dynamic and static weight deleting processes. The automatic weight deleting mechanism introduced in the present study is based on the optimal RMS error variation. In this case, once the RMS error drops to the desired level, weight deleting process starts, which then enables one to select the optimal threshold automatically, in this case, RMS error becomes minimum. The study is extended to include two sets of data structures, namely first and second data kinds. In the first data kind, random variables and coefficients in equations governing the chart patterns are varied while in the second data kind, only random variables are changed. These enable one to compare the generalization capacity of the resulting network which uses the first and second data kinds separately. It is found that dynamic deleting process results improved performances and the late start of deleting process is fruitful for improved learning rate. In addition, the use of first data kind provides the network with better generalization capacity." @default.
- W2038388994 created "2016-06-24" @default.
- W2038388994 creator A5027943848 @default.
- W2038388994 creator A5048221219 @default.
- W2038388994 date "1998-11-01" @default.
- W2038388994 modified "2023-09-26" @default.
- W2038388994 title "Simulation of weight prunning process in backpropagation neural network for pattern classification: A self-running threshold approach" @default.
- W2038388994 cites W1985309513 @default.
- W2038388994 cites W2097533491 @default.
- W2038388994 doi "https://doi.org/10.1016/s0045-7825(98)00072-3" @default.
- W2038388994 hasPublicationYear "1998" @default.
- W2038388994 type Work @default.
- W2038388994 sameAs 2038388994 @default.
- W2038388994 citedByCount "4" @default.
- W2038388994 countsByYear W20383889942020 @default.
- W2038388994 countsByYear W20383889942021 @default.
- W2038388994 crossrefType "journal-article" @default.
- W2038388994 hasAuthorship W2038388994A5027943848 @default.
- W2038388994 hasAuthorship W2038388994A5048221219 @default.
- W2038388994 hasConcept C111919701 @default.
- W2038388994 hasConcept C11413529 @default.
- W2038388994 hasConcept C115961682 @default.
- W2038388994 hasConcept C147764199 @default.
- W2038388994 hasConcept C154945302 @default.
- W2038388994 hasConcept C155032097 @default.
- W2038388994 hasConcept C191178318 @default.
- W2038388994 hasConcept C199360897 @default.
- W2038388994 hasConcept C41008148 @default.
- W2038388994 hasConcept C50644808 @default.
- W2038388994 hasConcept C98045186 @default.
- W2038388994 hasConceptScore W2038388994C111919701 @default.
- W2038388994 hasConceptScore W2038388994C11413529 @default.
- W2038388994 hasConceptScore W2038388994C115961682 @default.
- W2038388994 hasConceptScore W2038388994C147764199 @default.
- W2038388994 hasConceptScore W2038388994C154945302 @default.
- W2038388994 hasConceptScore W2038388994C155032097 @default.
- W2038388994 hasConceptScore W2038388994C191178318 @default.
- W2038388994 hasConceptScore W2038388994C199360897 @default.
- W2038388994 hasConceptScore W2038388994C41008148 @default.
- W2038388994 hasConceptScore W2038388994C50644808 @default.
- W2038388994 hasConceptScore W2038388994C98045186 @default.
- W2038388994 hasLocation W20383889941 @default.
- W2038388994 hasOpenAccess W2038388994 @default.
- W2038388994 hasPrimaryLocation W20383889941 @default.
- W2038388994 hasRelatedWork W1496211291 @default.
- W2038388994 hasRelatedWork W1605883667 @default.
- W2038388994 hasRelatedWork W1810398451 @default.
- W2038388994 hasRelatedWork W2049273722 @default.
- W2038388994 hasRelatedWork W2101976176 @default.
- W2038388994 hasRelatedWork W2113136428 @default.
- W2038388994 hasRelatedWork W2125644289 @default.
- W2038388994 hasRelatedWork W2131987051 @default.
- W2038388994 hasRelatedWork W2140502543 @default.
- W2038388994 hasRelatedWork W2150634210 @default.
- W2038388994 hasRelatedWork W2391996455 @default.
- W2038388994 hasRelatedWork W2976426989 @default.
- W2038388994 hasRelatedWork W3042063146 @default.
- W2038388994 hasRelatedWork W3206043183 @default.
- W2038388994 hasRelatedWork W813345349 @default.
- W2038388994 hasRelatedWork W2785180770 @default.
- W2038388994 hasRelatedWork W2840655365 @default.
- W2038388994 hasRelatedWork W2966746915 @default.
- W2038388994 hasRelatedWork W2967448279 @default.
- W2038388994 hasRelatedWork W3181004184 @default.
- W2038388994 isParatext "false" @default.
- W2038388994 isRetracted "false" @default.
- W2038388994 magId "2038388994" @default.
- W2038388994 workType "article" @default.