Journal of Physics Conference Series · 2019 · 33 citations · 0 references
EngineeringIntelligent SystemsSocial SciencesPattern RecognitionCharacter RecognitionNeurocomputersComputer ScienceStatistical Pattern RecognitionHidden LayerCase StudiesEvolving Neural NetworkArtificial Neural NetworksCellular Neural NetworkComputational NeuroscienceCase StudyNeuronal NetworkNeuroscienceBrain-like ComputingArtificial Neural NetworkPattern Recognition Application
Abstract This paper presents the analyst the number of layers and the number of neurons in the hidden layer of the Artificial Neural Network. In this study, case studies were taken in the recognition of alphabet patterns and shape patterns. First, the number of layers is varied to get the best number of layers. Furthermore, the number of neurons is varied to get the best number of neurons. The results showed that the best number of layers was 1-5 layers in the hidden layer, with validation values from the recognition system 96-100%. While the best number of neurons is obtained with 19 neurons, with an average accuracy percentage of 81%.