A hybrid ART-GRNN online learning neural network with a ?-insensitive loss function

• Main Authors: Yap K.S., Lim C.P., Abidin I.Z.
• 其他作者: 24448864400
• 格式: Article
• 出版: 2023
• 主題: Adaptive resonance theory (ART); Bayesian theorem; Generalized regression neural network (GRNN); Online sequential extreme learning machine; Algorithms; Artificial Intelligence; Computer Simulation; Models, Theoretical; Neural Networks (Computer); Online Systems; Pattern Recognition, Automated; Arts computing; E-learning; Education; Feedforward neural networks; Food processing; Image classification; Internet; Learning systems; Radial basis function networks; Resonance; Time series analysis; algorithm; article; artificial intelligence; artificial neural network; automated pattern recognition; computer simulation; methodology; online system; theoretical model; Adaptive resonance theories; Adaptive resonance theory; Empirical studies; Extreme Learning Machine; Gaussian; Generalized regression neural network; Hybrid model; Loss functions; Neural network modelling; On-line learning; Radial basis function neural networks; Sequential learning; Time-series prediction; Neural networks

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models. � 2008 IEEE.