ML method Learning approach  ANN, MLP Supervised  RBFNN
Supervised  DNN Supervised  Decision tree, ID3 Supervised  Adaptive neurofuzzy Hybrid  Neurofuzzy system Hybrid  Fusion of classifiers Hybrid (Bayesian, SVM, k-nearest neighbor)  Neurofuzzy system Hybrid  ANN + MLP, RBFNN
Hybrid  Neurofuzzy system Hybrid  PBL-McRBFN Supervised  Multistate Markov model Hybrid  Random tree, (C-RT), ID3, binary logistic regression, Supervised k-NN, (PLS), (SVM)  FCM Unsupervised Size of Number of Work ref.
In this paper, a measurement model is built to calculate the R-P&O of large-volume components by parallel ranging, and an intelligent algorithm combining RBFNN
 and DE  is proposed to solve the model in Section 2.
Based on the implicit function theorem, the RBFNN
is introduced to accurately approximate the unknown function of the model.
Caption: FIGURE 6: Flow chart of MMAGA optimization of RBFNN
It has been well recognized that, using the powerful approximate ability of the RBFNN
, we can approximate any continuous nonlinear function over a compact set as
To solve this problem radial basis function neural network (RBFNN
) based PSS with single machine connected at infinite bus (SMIB) model is proposed by taking angular frequency as an input to improve the transient and dynamic stability of electrical power system at varying loads.
Polat, "Estimation of local SAR level using RBFNN
in three-layer cylindrical human model," Microwave and Optical Technology Letters, Vol.
West (2000) tests five NN architectures (multilayer perceptron (MLP), mixture-of-experts (MOE), RBFNN
, learning vector quantization (LVQ), and fuzzy adaptive resonance (FAR) against LDA, LR, kNN, kernel density estimation (KDE), and DTs on credit datasets from the University of Hamburg (Germany) and Australia using 10-fold cross-validation.
Literature Features Classifier Classes Accuracy Ubeyli  Lyapunov exponents ANN 4 93.9 and wavelet classifier coefficients Korurek and Temporal feature PSO and 6 96.3 Dogan  set RBFNN
de Chazal Morphology and Linear 5 85.9 and heartbeat interval discriminant Reilly  Inan et WT + timing ANN 3 95.2 al.
The proposed method uses radial basis function neural network (RBFNN
) to extend the input matrix.
In radial basis function neural network (RBFNN
), the hidden nodes are implementing a set of radial basis functions (e.g., Gaussian functions).
In  OLS based RBFNN
is proposed to optimize the parameters of the network for transformer fault diagnosis.