Neuro-fuzzy and Soft Computing: A Computational Approach to Learning and Machine IntelligenceNeuro-Fuzzy and Soft Computing provides the first comprehensive treatment of the constituent methodologies underlying neuro-fuzzy and soft computing, an evolving branch of computational intelligence. The constituent methodologies include fuzzy set theory, neural networks, data clustering techniques, and several stochastic optimization methods that do not require gradient information. In particular, the authors put equal emphasis on theoretical aspects of covered methodologies, as well as empirical observations and verifications of various applications in practice. The book is well suited for use as a text for courses on computational intelligence and as a single reference source for this emerging field. To help readers understand the material the presentation includes more than 50 examples, more than 150 exercises, over 300 illustrations, and more than 150 Matlab scripts. In addition, Matlab is utilized to visualize the processes of fuzzy reasoning, neural-network learning, neuro-fuzzy integration and training, and gradient-free optimization (such as genetic algorithms, simulated annealing, random search, and downhill Simplex method). The presentation also makes use of SIMULINK for neuro-fuzzy control system simulations. All Matlab scripts used in the book are available on the free companion software disk that may be ordered by using the enclosed reply card. The book also contains an "Internet Resource Page" to point the reader to on-line neuro-fuzzy and soft computing home pages, publications, public-domain software, research institutes, news groups, etc. All the HTTP and FTP addresses are available as a bookmark file on the companion software disk. |
Contents
Introduction to NeuroFuzzy and Soft Computing | 1 |
Fuzzy Sets | 13 |
Exercises | 47 |
22 other sections not shown
Common terms and phrases
action adaptive network ANFIS applications approach approximation architecture backpropagation backpropagation MLP bell MF binary CANFIS Chapter chromosome cluster centers Coach color crossover curves data pairs data points data set defined defuzzification denoted derivative descent method discussed dynamics Equation error measure example firing strength formula fuzzy controller fuzzy inference system fuzzy logic fuzzy relations fuzzy rules fuzzy set Gaussian genetic algorithms gradient Hopfield identification initial input space input-output iteration learning rule linear linguistic MATLAB file matrix membership functions Membership Grades minimize neural networks neuro-fuzzy neuron node nonlinear objective function obtained operator optimization output unit parameters partition pattern perceptron performance pole length prediction problem procedure Q-learning radial basis function RBFN receptive field reinforcement learning Section shown in Figure sigmoidal functions signal simulation soft computing steepest descent step structure supervised learning T-norm techniques tion Touretzky training data tree update variables vertex weights