Matches in SemOpenAlex for { <https://semopenalex.org/work/W2172018238> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2172018238 abstract "The paper presents two ways of improving the handwritten digit recognition ability of a neural network. First by selection of the number of hidden units in the neural network, and second, by training using an augmented set of patterns. The handwritten digit recognition application is performed on feed-forward, fully connected neural networks with two hidden layer architectures. A genetic algorithm is used to search among configurations of two unequal hidden layer networks to find the optimum number of hidden units. Training procedures involving augmented sets of training patterns are produced by two methods: by shifting and by magnification every handwritten digit of the original training set. Results show that the best two hidden layer network, 178/spl times/26 units, trained for 10 different random starting weight sets in centered mode, i.e., no shifting, resulted in 82.74% average recognition rate with standard deviation, STD=0.66. The best two hidden layer network, 154/spl times/58, trained for 11 different random starting weight sets in shifting mode, resulted in 92.09% average recognition rate with STD=0.37. A comparison of recognition rates for centered versus shifting training modes for the genetic selection resulted statistically significant with p<0.001." @default.
- W2172018238 created "2016-06-24" @default.
- W2172018238 creator A5012413674 @default.
- W2172018238 creator A5048514196 @default.
- W2172018238 date "2002-11-23" @default.
- W2172018238 modified "2023-09-27" @default.
- W2172018238 title "Improvements on handwritten digit recognition by genetic selection of neural network topology and by augmented training" @default.
- W2172018238 cites W1978004231 @default.
- W2172018238 cites W2052627427 @default.
- W2172018238 cites W2078376347 @default.
- W2172018238 cites W2100816322 @default.
- W2172018238 cites W2103575890 @default.
- W2172018238 cites W2152596143 @default.
- W2172018238 cites W2153526431 @default.
- W2172018238 cites W2156728410 @default.
- W2172018238 cites W2166843422 @default.
- W2172018238 cites W2201098670 @default.
- W2172018238 doi "https://doi.org/10.1109/icsmc.1997.638199" @default.
- W2172018238 hasPublicationYear "2002" @default.
- W2172018238 type Work @default.
- W2172018238 sameAs 2172018238 @default.
- W2172018238 citedByCount "10" @default.
- W2172018238 countsByYear W21720182382012 @default.
- W2172018238 crossrefType "proceedings-article" @default.
- W2172018238 hasAuthorship W2172018238A5012413674 @default.
- W2172018238 hasAuthorship W2172018238A5048514196 @default.
- W2172018238 hasConcept C121144440 @default.
- W2172018238 hasConcept C153180895 @default.
- W2172018238 hasConcept C154945302 @default.
- W2172018238 hasConcept C175202392 @default.
- W2172018238 hasConcept C177264268 @default.
- W2172018238 hasConcept C178790620 @default.
- W2172018238 hasConcept C185592680 @default.
- W2172018238 hasConcept C199360897 @default.
- W2172018238 hasConcept C2779227376 @default.
- W2172018238 hasConcept C28490314 @default.
- W2172018238 hasConcept C2984784707 @default.
- W2172018238 hasConcept C41008148 @default.
- W2172018238 hasConcept C50644808 @default.
- W2172018238 hasConcept C81917197 @default.
- W2172018238 hasConceptScore W2172018238C121144440 @default.
- W2172018238 hasConceptScore W2172018238C153180895 @default.
- W2172018238 hasConceptScore W2172018238C154945302 @default.
- W2172018238 hasConceptScore W2172018238C175202392 @default.
- W2172018238 hasConceptScore W2172018238C177264268 @default.
- W2172018238 hasConceptScore W2172018238C178790620 @default.
- W2172018238 hasConceptScore W2172018238C185592680 @default.
- W2172018238 hasConceptScore W2172018238C199360897 @default.
- W2172018238 hasConceptScore W2172018238C2779227376 @default.
- W2172018238 hasConceptScore W2172018238C28490314 @default.
- W2172018238 hasConceptScore W2172018238C2984784707 @default.
- W2172018238 hasConceptScore W2172018238C41008148 @default.
- W2172018238 hasConceptScore W2172018238C50644808 @default.
- W2172018238 hasConceptScore W2172018238C81917197 @default.
- W2172018238 hasLocation W21720182381 @default.
- W2172018238 hasOpenAccess W2172018238 @default.
- W2172018238 hasPrimaryLocation W21720182381 @default.
- W2172018238 hasRelatedWork W1497424843 @default.
- W2172018238 hasRelatedWork W2000406544 @default.
- W2172018238 hasRelatedWork W2012191176 @default.
- W2172018238 hasRelatedWork W2018813195 @default.
- W2172018238 hasRelatedWork W2021760654 @default.
- W2172018238 hasRelatedWork W2046195244 @default.
- W2172018238 hasRelatedWork W2063311813 @default.
- W2172018238 hasRelatedWork W2095538532 @default.
- W2172018238 hasRelatedWork W2097316030 @default.
- W2172018238 hasRelatedWork W2100816322 @default.
- W2172018238 hasRelatedWork W2118312153 @default.
- W2172018238 hasRelatedWork W2118716571 @default.
- W2172018238 hasRelatedWork W2127230358 @default.
- W2172018238 hasRelatedWork W2128976882 @default.
- W2172018238 hasRelatedWork W2131204291 @default.
- W2172018238 hasRelatedWork W2133940143 @default.
- W2172018238 hasRelatedWork W2151129782 @default.
- W2172018238 hasRelatedWork W2154288735 @default.
- W2172018238 hasRelatedWork W2183064810 @default.
- W2172018238 hasRelatedWork W2525962964 @default.
- W2172018238 isParatext "false" @default.
- W2172018238 isRetracted "false" @default.
- W2172018238 magId "2172018238" @default.
- W2172018238 workType "article" @default.