Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence
Neuro-Fuzzy Modeling and Soft Computing places particular emphasis on the theoretical aspects of covered methodologies, as well as empirical observations and verifications of various applications in practice. Neuro-Fuzzy Modeling and Soft Computing is oriented toward methodologies that are likely to be of practical use. It includes exercises, some of which involve MATLAB programming tasks to provide readers with hands-on programming experiences for practical problem-solving. Each chapter also includes a reference list to the research literature so that readers may pursue topics in greater depth. This book is suitable as a self-study guide by researchers who want to learn basic and advanced neuro-fuzzy and soft computing within the framework of computational intelligence.
39 pages matching supervised learning in this book
Results 1-3 of 39
Introduction to NeuroFuzzy and Soft Computing
Fuzzy Rules and Fuzzy Reasoning
22 other sections not shown
action adaptive network ANFIS applications approach approximation architecture backpropagation backpropagation MLP bell MF binary CANFIS Chapter chromosome cluster centers color crossover curves data pairs data points data set defined defuzzification denoted derivative descent method dynamics Equation error measure example firing strength formula fuzzy controller fuzzy if-then rules fuzzy inference system fuzzy logic fuzzy relations fuzzy rules fuzzy set Gaussian genetic algorithms gradient ha(x Hopfield identification initial input space input-output iteration learning rule linear linguistic MATLAB file matrix membership functions minimize modified neural networks neuro-fuzzy neuron nonlinear objective function obtained operator optimization output unit parameters partition pattern perceptron performance prediction problem procedure Q-learning radial basis function random RBFN receptive field reinforcement learning shown in Figure sigmoidal functions signal simulated annealing simulation soft computing steepest descent step structure supervised learning T-norm techniques tion Touretzky training data tree update variables vertex weights
All Book Search results »
Nonlinear System Identification: From Classical Approaches to Neural ...
Limited preview - 2001