Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788355949> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2788355949 abstract "Artificial neural networks are very useful in classification and function approximation tasks and there exists various algorithms for training a neural network. In past decade, one such decent and novel algorithm, extreme learning machine (ELM) has received attention due to its fast learning rate and better generalization ability in contrast to orthodox gradient descent learning algorithms for single-hidden-layer feed forward neural network. Despite it’s advantages, the single-hidden-layer feed forward neural network trained using ELM require more number of hidden neurons and faces poor condition problem as the input weights and hidden biases are randomly created. One way to overcome this problem is to use an optimization technique for finding an optimum set of input weights. In this work, we have proposed a hybrid learning scheme which uses one such optimisation technique called cat swarm optimization (CSO) to find an optimum set of input-hidden node weights and then this set of optimal input weights is used to analytically determine the output weights by using Moore-Penrose generalized inverse. Some optimisation techniques have been previously proposed like particle swarm optimisation but not CSO. In this work, modifications have been made to the existing CSO technique with the specific goal of further improving the generalization performance as well as the reducing the poor condition of networks trained using ELM. The proposed modifications 1) help in improving the search diversity of CSO, which allows better exploration of the solution search space and 2) improves the condition of the SLFN trained using ELM by including the norm of output weights in the evolutionary operator. Three standard benchmark datasets have been collected from the UCI machine learning repository to validate the performance of the proposed scheme and comparative analysis has been made with other state of the art optimisation techniques. The proposed scheme, along with other evolutionary algorithms, requires a smaller number of hidden neuron compared to traditional the ELM for attaining almost similar classification accuracy. The experimental results also show that the proposed hybrid approach is able to produce well condition SLFNs with much better generalization performance." @default.
- W2788355949 created "2018-03-06" @default.
- W2788355949 creator A5026483682 @default.
- W2788355949 date "2017-05-01" @default.
- W2788355949 modified "2023-09-27" @default.
- W2788355949 title "An Improved Extreme Learning Machine Using Cat Swarm Optimization" @default.
- W2788355949 hasPublicationYear "2017" @default.
- W2788355949 type Work @default.
- W2788355949 sameAs 2788355949 @default.
- W2788355949 citedByCount "0" @default.
- W2788355949 crossrefType "dissertation" @default.
- W2788355949 hasAuthorship W2788355949A5026483682 @default.
- W2788355949 hasConcept C108037233 @default.
- W2788355949 hasConcept C11413529 @default.
- W2788355949 hasConcept C119857082 @default.
- W2788355949 hasConcept C126255220 @default.
- W2788355949 hasConcept C134306372 @default.
- W2788355949 hasConcept C152153834 @default.
- W2788355949 hasConcept C153258448 @default.
- W2788355949 hasConcept C154945302 @default.
- W2788355949 hasConcept C156738730 @default.
- W2788355949 hasConcept C177148314 @default.
- W2788355949 hasConcept C177264268 @default.
- W2788355949 hasConcept C199360897 @default.
- W2788355949 hasConcept C2780150128 @default.
- W2788355949 hasConcept C33923547 @default.
- W2788355949 hasConcept C41008148 @default.
- W2788355949 hasConcept C47702885 @default.
- W2788355949 hasConcept C50644808 @default.
- W2788355949 hasConcept C555944384 @default.
- W2788355949 hasConcept C76155785 @default.
- W2788355949 hasConcept C85617194 @default.
- W2788355949 hasConceptScore W2788355949C108037233 @default.
- W2788355949 hasConceptScore W2788355949C11413529 @default.
- W2788355949 hasConceptScore W2788355949C119857082 @default.
- W2788355949 hasConceptScore W2788355949C126255220 @default.
- W2788355949 hasConceptScore W2788355949C134306372 @default.
- W2788355949 hasConceptScore W2788355949C152153834 @default.
- W2788355949 hasConceptScore W2788355949C153258448 @default.
- W2788355949 hasConceptScore W2788355949C154945302 @default.
- W2788355949 hasConceptScore W2788355949C156738730 @default.
- W2788355949 hasConceptScore W2788355949C177148314 @default.
- W2788355949 hasConceptScore W2788355949C177264268 @default.
- W2788355949 hasConceptScore W2788355949C199360897 @default.
- W2788355949 hasConceptScore W2788355949C2780150128 @default.
- W2788355949 hasConceptScore W2788355949C33923547 @default.
- W2788355949 hasConceptScore W2788355949C41008148 @default.
- W2788355949 hasConceptScore W2788355949C47702885 @default.
- W2788355949 hasConceptScore W2788355949C50644808 @default.
- W2788355949 hasConceptScore W2788355949C555944384 @default.
- W2788355949 hasConceptScore W2788355949C76155785 @default.
- W2788355949 hasConceptScore W2788355949C85617194 @default.
- W2788355949 hasLocation W27883559491 @default.
- W2788355949 hasOpenAccess W2788355949 @default.
- W2788355949 hasPrimaryLocation W27883559491 @default.
- W2788355949 hasRelatedWork W1506983422 @default.
- W2788355949 hasRelatedWork W1647227861 @default.
- W2788355949 hasRelatedWork W1976350960 @default.
- W2788355949 hasRelatedWork W2002984713 @default.
- W2788355949 hasRelatedWork W2010030411 @default.
- W2788355949 hasRelatedWork W2015909866 @default.
- W2788355949 hasRelatedWork W2106427050 @default.
- W2788355949 hasRelatedWork W2134761066 @default.
- W2788355949 hasRelatedWork W2145121462 @default.
- W2788355949 hasRelatedWork W2416378803 @default.
- W2788355949 hasRelatedWork W2590142046 @default.
- W2788355949 hasRelatedWork W2757443524 @default.
- W2788355949 hasRelatedWork W2790025164 @default.
- W2788355949 hasRelatedWork W2796196919 @default.
- W2788355949 hasRelatedWork W2809600276 @default.
- W2788355949 hasRelatedWork W2823492219 @default.
- W2788355949 hasRelatedWork W2896050579 @default.
- W2788355949 hasRelatedWork W2896230333 @default.
- W2788355949 hasRelatedWork W3021548483 @default.
- W2788355949 hasRelatedWork W2116095820 @default.
- W2788355949 isParatext "false" @default.
- W2788355949 isRetracted "false" @default.
- W2788355949 magId "2788355949" @default.
- W2788355949 workType "dissertation" @default.