DOAJ (DOAJ: Directory of Open Access Journals) · 2015 · 35 citations · 0 references
ComputingComputer ScienceComputer VisionDiagnostic ImagingMachine LearningDeep LearningImage ReconstructionImage RestorationLoss FunctionNeural NetworksOverfittingImage Reconstruction AlgorithmsMultilayer PerceptronReconstruction Algorithms
Abstract Recently back propagation neural network BPNN has been applied successfully in many areas with excellent generalization results for example rule extraction classification and evaluation. In this paper the Levenberg-Marquardt back-propagation algorithm is used for training the network and reconstructs the image. It is found that Marquardt algorithm is significantly more proficient. A practical problem with MLPs is to select the correct complexity for the model i.e. the right number of hidden units or correct regularization parameters. In this paper a study is made to determine the issue of number of neurons in every hidden layer and the quantity of hidden layers needed for getting the high accuracy. We performed regression R analysis to measure the correlation between outputs and targets.