eCite Digital Repository (University of Tasmania) · 2008 · 180 citations · 9 references
Open access
ComputingComputer ScienceFinanceArtificial IntelligenceData MiningMachine LearningNeural Data AnalysisNeural NetworksOptimization For Machine LearningPattern RecognitionRepresentation LearningFeedforward Neural NetworksMathematical JustificationMultilayer PerceptronNeural Network ClassificationNeural Network ModelingNeural Network PredictionPerceptron
Optimizing the number of hidden layerneurons for an FNN (feedforward neural network) tosolve a practical problem remains one of the unsolvedtasks in this research area. In this paper we reviewseveral mechanisms in the neural networks literaturewhich have been used for determining an optimalnumber of hidden layer neuron (given an application),propose our new approach based on some mathematicalevidence, and apply it in financial data mining.Compared with the existing methods, our new approachis proven (with mathematical justification), and can beeasily handled by users from all application fields.
9
Data mining: concepts and techniques
Jiawei Han, Micheline Kamber · Choice Reviews Online · 2012 · 28.9K citations
Dynamic Node Creation in Backpropagation Networks
Timur Ash · Connection Science · 1989 · 413 citations