Matches in SemOpenAlex for { <https://semopenalex.org/work/W2081571497> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2081571497 abstract "Radial Basis Function (RBF) Network is popularly used for solving pattern recognition problems. The training of RBF Network is faster compared to multi layer perceptron using error backpropagation. However, the RBF Network uses the pseudo inverse matrix to calculate weights from the hidden layer to the output layer. Thus calculation cost increases when the number of data and the number of hidden units increase. In addition, in RBF Network the decision of optimum number of hidden units is difficult. It is also more prone to overtraining, needing repeated train and test cycles to ascertain a proper number of the Network hidden units, so that generalization performance is good. In this work, we propose a technique to set up RBF network parameters which is fast, as well as the number of hidden units are automatically determined. We start with training a Self-Organizing Maps (SOM), which is a unsupervised training, though our samples are labeled. SOM can find the distribution of data in multidimensional space, and map it on a two dimensional display. The results of SOM network is used to calculate the RBF parameters. It is shown by experiments that using the proposed method, RBF network parameters can be determined much faster compared to existing technique. Moreover, the recognition rate for the test data was higher, showing better generalization performance." @default.
- W2081571497 created "2016-06-24" @default.
- W2081571497 creator A5000954580 @default.
- W2081571497 creator A5031836646 @default.
- W2081571497 creator A5034975231 @default.
- W2081571497 creator A5063978809 @default.
- W2081571497 date "2010-06-01" @default.
- W2081571497 modified "2023-09-24" @default.
- W2081571497 title "An Efficient Method to Set RBF Network Paramters Based on SOM Training" @default.
- W2081571497 cites W1524100745 @default.
- W2081571497 cites W1679913846 @default.
- W2081571497 cites W1980290744 @default.
- W2081571497 cites W1991848143 @default.
- W2081571497 cites W2065923787 @default.
- W2081571497 cites W2086002125 @default.
- W2081571497 cites W2110916332 @default.
- W2081571497 cites W2124222487 @default.
- W2081571497 cites W2133218851 @default.
- W2081571497 cites W2155399784 @default.
- W2081571497 cites W2171277043 @default.
- W2081571497 cites W2280006202 @default.
- W2081571497 cites W2933515137 @default.
- W2081571497 doi "https://doi.org/10.1109/cit.2010.99" @default.
- W2081571497 hasPublicationYear "2010" @default.
- W2081571497 type Work @default.
- W2081571497 sameAs 2081571497 @default.
- W2081571497 citedByCount "1" @default.
- W2081571497 countsByYear W20815714972014 @default.
- W2081571497 crossrefType "proceedings-article" @default.
- W2081571497 hasAuthorship W2081571497A5000954580 @default.
- W2081571497 hasAuthorship W2081571497A5031836646 @default.
- W2081571497 hasAuthorship W2081571497A5034975231 @default.
- W2081571497 hasAuthorship W2081571497A5063978809 @default.
- W2081571497 hasConcept C111168008 @default.
- W2081571497 hasConcept C132917294 @default.
- W2081571497 hasConcept C134306372 @default.
- W2081571497 hasConcept C153180895 @default.
- W2081571497 hasConcept C154945302 @default.
- W2081571497 hasConcept C155032097 @default.
- W2081571497 hasConcept C177148314 @default.
- W2081571497 hasConcept C179717631 @default.
- W2081571497 hasConcept C182016430 @default.
- W2081571497 hasConcept C33923547 @default.
- W2081571497 hasConcept C41008148 @default.
- W2081571497 hasConcept C50644808 @default.
- W2081571497 hasConcept C60908668 @default.
- W2081571497 hasConcept C98856871 @default.
- W2081571497 hasConceptScore W2081571497C111168008 @default.
- W2081571497 hasConceptScore W2081571497C132917294 @default.
- W2081571497 hasConceptScore W2081571497C134306372 @default.
- W2081571497 hasConceptScore W2081571497C153180895 @default.
- W2081571497 hasConceptScore W2081571497C154945302 @default.
- W2081571497 hasConceptScore W2081571497C155032097 @default.
- W2081571497 hasConceptScore W2081571497C177148314 @default.
- W2081571497 hasConceptScore W2081571497C179717631 @default.
- W2081571497 hasConceptScore W2081571497C182016430 @default.
- W2081571497 hasConceptScore W2081571497C33923547 @default.
- W2081571497 hasConceptScore W2081571497C41008148 @default.
- W2081571497 hasConceptScore W2081571497C50644808 @default.
- W2081571497 hasConceptScore W2081571497C60908668 @default.
- W2081571497 hasConceptScore W2081571497C98856871 @default.
- W2081571497 hasLocation W20815714971 @default.
- W2081571497 hasOpenAccess W2081571497 @default.
- W2081571497 hasPrimaryLocation W20815714971 @default.
- W2081571497 hasRelatedWork W1517968461 @default.
- W2081571497 hasRelatedWork W1549288338 @default.
- W2081571497 hasRelatedWork W1550123614 @default.
- W2081571497 hasRelatedWork W1571551140 @default.
- W2081571497 hasRelatedWork W1580089141 @default.
- W2081571497 hasRelatedWork W1680063279 @default.
- W2081571497 hasRelatedWork W1833345539 @default.
- W2081571497 hasRelatedWork W1886615868 @default.
- W2081571497 hasRelatedWork W2018769829 @default.
- W2081571497 hasRelatedWork W2027727497 @default.
- W2081571497 hasRelatedWork W2045939648 @default.
- W2081571497 hasRelatedWork W2049937414 @default.
- W2081571497 hasRelatedWork W2099283460 @default.
- W2081571497 hasRelatedWork W2099377044 @default.
- W2081571497 hasRelatedWork W2113356811 @default.
- W2081571497 hasRelatedWork W2116119284 @default.
- W2081571497 hasRelatedWork W2145662860 @default.
- W2081571497 hasRelatedWork W2151291194 @default.
- W2081571497 hasRelatedWork W2370361000 @default.
- W2081571497 hasRelatedWork W2489777820 @default.
- W2081571497 isParatext "false" @default.
- W2081571497 isRetracted "false" @default.
- W2081571497 magId "2081571497" @default.
- W2081571497 workType "article" @default.