Radial basis function (RBF) neural network is a kind of three-layer feedforward neural network with single hidden layer, there is great difference between it's structure and learning algorithms with BP neural network's.
Fuzzy logic system is represented by a forward fuzzy neural network which has two hidden layers,the fast learning method is used to adjust initial rule base parameter to get an optimal fuzzy controller,simulation result shows control performance is improved significantly.
With the neural network based model,343 training set data and 216 verification set data according to the principle with LOG space and 64 data sets according to even distribution are used to verify the training results and test the modeling performance. The case study shows that the converging speed,the training time and the accuracy of the model with two hidden layers are very satisfactory. The average precision of the color notation conversion of the model established is less than 0.6 CIELUV unit.
In order to improve BP Network's generalizing ability and convergent speed, a new algorithm based on entropy method and an improved energy function is proposed, its efficiency is proved by experiments.
The relationship between the order of approximation by neural network based on scattered threshold value nodes and the neurons involved in a single hidden layer is investigated.
In this paper, we propose a new directional multi-resolution ridgelet network (DMRN) based on the ridgelet frame theory, which uses the ridgelet as the activation function in a hidden layer.
The results obtained earlier are extended to the cases of a nonlinear regression and a feedforward neural network with one hidden layer.
Multilayer Perceptrons with different numbers of neurons in the hidden layer have been trained using different values of the signal-to-noise ratio to minimize the mean square error using the error back-propagation algorithm.
The best predictive power for the classification of soils from the fifteen regions was achieved using a network with seven hidden layer nodes and 2500 training epochs using the online back-propagation randomized training algorithm.
The attribute reduction algorithm of the discernibility matrix is used for the optimization design of reducing nodes of input and hidden layers.
Each network is a multi-layer perceptron with one or two hidden layers and a different number of hidden neurons.
The fuzzy neural network has six layers, including input layer, output layer and four hidden layers.
These variables served as input variables for neural network technique classification, taking 12 input variables, 2 hidden layers and 7 outcome variables for 0=Movement Time, 1=Wake, 2=REM, 3=S1, 4=S2, 5=S3 and 6=S4.
The design of an NN involves the choice of several parameters which include the network architecture, number of hidden layers, number of neurons in the hidden layers, training, learning and transfer functions.
In this paper, the property that a multi-layered neural network can describe any bounded nonlinear function is analyzed and verified by simulation experiment. The effect of the number of hidden layer neurons on network output is also analyzed, and the simulation results are given.