What people are saying - Write a review
We haven't found any reviews in the usual places.
An Introduction to Learning Modelling and Control
Neural Networks for Modelling and Control
Associative Memory Networks
12 other sections not shown
AMNs approximation autocorrelation matrix B-spline basis functions B-spline network calculated Chapter CMAC CMAC network considered consistency equations defined defuzzification depends derived described desired function displacement vector eigenvalues fuzzy algorithm fuzzy controller fuzzy input set fuzzy logic fuzzy rule fuzzy sets fuzzy system Gaussian generalisation parameter gradient descent hidden layer implement initialised input space iteration knots learning algorithm learning interference learning rate learning rules linear look-up table mapping membership functions minimal capture zone modelling and control modelling capabilities modelling error multivariate basis functions n-dimensional network output Neural Networks node non-zero nonlinear normalised number of basis on-line operator optimisation orthogonal functions output error overlay displacement parameter convergence partition of unity Perceptron piecewise plant model polynomial produces rate of convergence representation rule base Section shown in Figure signal solution hyperplane spline stored structure training data training examples transformed input vector two-dimensional univariate basis functions weight space weight updates weight vector zero
All Book Search results »
Nonlinear System Identification: From Classical Approaches to Neural ...
Limited preview - 2001