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

• المؤلفون الرئيسيون: Yap K.S., Lim C.P., Abidin I.Z.
• مؤلفون آخرون: 24448864400
• التنسيق: مقال
• منشور في: 2023
• الموضوعات: 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 pr...