Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969768139> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2969768139 abstract "An artificial (ANN), or shortly neural network (NN), is a powerfulmathematical or computational model that is inspired by the structure and/orfunctional characteristics of biological networks. Despite the fact that ANN hasbeen developing rapidly for many years, there are still some challenges concerningthe development of an ANN model that performs effectively for the problem at hand.ANN can be categorized into three main types: single layer, recurrent andmultilayer feed-forward network. In multilayer feed-forward ANN, the actualperformance is highly dependent on the selection of architecture and trainingparameters. However, a systematic method for optimizing these parameters is still anactive research area. This work focuses on multilayer feed-forward ANNs due to theirgeneralization capability, simplicity from the viewpoint of structure, and ease ofmathematical analysis. Even though, several rules for the optimization of multilayerfeed-forward ANN parameters are available in the literature, most networks are stillcalibrated via a trial-and-error procedure, which depends mainly on the type ofproblem, and past experience and intuition of the expert. To overcome theselimitations, there have been attempts to use genetic algorithm (GA) to optimize someof these parameters. However most, if not all, of the existing approaches are focusedpartially on the part of architecture and training parameters. On the contrary, the GAANNapproach presented here has covered most aspects of multilayer feed-forwardANN in a more comprehensive way. This research focuses on the use of binaryencodedgenetic algorithm (GA) to implement efficient search strategies for theoptimal architecture and training parameters of a multilayer feed-forward ANN.Particularly, GA is utilized to determine the optimal number of hidden layers, numberof neurons in each hidden layer, type of training algorithm, type of activation functionof hidden and output neurons, initial weight, learning rate, momentum term, andepoch size of a multilayer feed-forward ANN. In this thesis, the approach has beenanalyzed and algorithms that simulate the new approach have been mapped out." @default.
- W2969768139 created "2019-08-29" @default.
- W2969768139 creator A5008334284 @default.
- W2969768139 date "2011-01-01" @default.
- W2969768139 modified "2023-09-24" @default.
- W2969768139 title "PROPOSED METHODOLOGY FOR OPTIMIZING THE TRAININGPARAMETERS OF A MULTILAYER FEED-FORWARD ARTIFICIAL NEURALNETWORKS USING A GENETIC ALGORITHM" @default.
- W2969768139 hasPublicationYear "2011" @default.
- W2969768139 type Work @default.
- W2969768139 sameAs 2969768139 @default.
- W2969768139 citedByCount "0" @default.
- W2969768139 crossrefType "dissertation" @default.
- W2969768139 hasAuthorship W2969768139A5008334284 @default.
- W2969768139 hasConcept C111472728 @default.
- W2969768139 hasConcept C11413529 @default.
- W2969768139 hasConcept C119857082 @default.
- W2969768139 hasConcept C127413603 @default.
- W2969768139 hasConcept C132010649 @default.
- W2969768139 hasConcept C133731056 @default.
- W2969768139 hasConcept C134306372 @default.
- W2969768139 hasConcept C138885662 @default.
- W2969768139 hasConcept C154945302 @default.
- W2969768139 hasConcept C177148314 @default.
- W2969768139 hasConcept C33923547 @default.
- W2969768139 hasConcept C38858127 @default.
- W2969768139 hasConcept C41008148 @default.
- W2969768139 hasConcept C47702885 @default.
- W2969768139 hasConcept C50644808 @default.
- W2969768139 hasConcept C81917197 @default.
- W2969768139 hasConcept C8880873 @default.
- W2969768139 hasConceptScore W2969768139C111472728 @default.
- W2969768139 hasConceptScore W2969768139C11413529 @default.
- W2969768139 hasConceptScore W2969768139C119857082 @default.
- W2969768139 hasConceptScore W2969768139C127413603 @default.
- W2969768139 hasConceptScore W2969768139C132010649 @default.
- W2969768139 hasConceptScore W2969768139C133731056 @default.
- W2969768139 hasConceptScore W2969768139C134306372 @default.
- W2969768139 hasConceptScore W2969768139C138885662 @default.
- W2969768139 hasConceptScore W2969768139C154945302 @default.
- W2969768139 hasConceptScore W2969768139C177148314 @default.
- W2969768139 hasConceptScore W2969768139C33923547 @default.
- W2969768139 hasConceptScore W2969768139C38858127 @default.
- W2969768139 hasConceptScore W2969768139C41008148 @default.
- W2969768139 hasConceptScore W2969768139C47702885 @default.
- W2969768139 hasConceptScore W2969768139C50644808 @default.
- W2969768139 hasConceptScore W2969768139C81917197 @default.
- W2969768139 hasConceptScore W2969768139C8880873 @default.
- W2969768139 hasLocation W29697681391 @default.
- W2969768139 hasOpenAccess W2969768139 @default.
- W2969768139 hasPrimaryLocation W29697681391 @default.
- W2969768139 hasRelatedWork W1045481615 @default.
- W2969768139 hasRelatedWork W1565786147 @default.
- W2969768139 hasRelatedWork W1859651943 @default.
- W2969768139 hasRelatedWork W1927181533 @default.
- W2969768139 hasRelatedWork W2019103416 @default.
- W2969768139 hasRelatedWork W2073515924 @default.
- W2969768139 hasRelatedWork W2123620569 @default.
- W2969768139 hasRelatedWork W2187353251 @default.
- W2969768139 hasRelatedWork W22063485 @default.
- W2969768139 hasRelatedWork W2232260037 @default.
- W2969768139 hasRelatedWork W2308668357 @default.
- W2969768139 hasRelatedWork W2332492702 @default.
- W2969768139 hasRelatedWork W2478099720 @default.
- W2969768139 hasRelatedWork W2612753882 @default.
- W2969768139 hasRelatedWork W2889160483 @default.
- W2969768139 hasRelatedWork W2889527493 @default.
- W2969768139 hasRelatedWork W2967458794 @default.
- W2969768139 hasRelatedWork W3030617535 @default.
- W2969768139 hasRelatedWork W3091289136 @default.
- W2969768139 hasRelatedWork W54788556 @default.
- W2969768139 isParatext "false" @default.
- W2969768139 isRetracted "false" @default.
- W2969768139 magId "2969768139" @default.
- W2969768139 workType "dissertation" @default.