Fuzzy and neural approaches in engineering
Neural networks and fuzzy systems represent two distinct technologies that deal with uncertainty. This definitive book presents the fundamentals of both technologies, and demonstrates how to combine the unique capabilities of these two technologies for the greatest advantage. Steering clear of unnecessary mathematics, the book highlights a wide range of dynamic possibilities and offers numerous examples to illuminate key concepts. It also explores the value of relating genetic algorithms and expert systems to fuzzy and neural technologies.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Introduction to Hybrid Artificial Intelligence
Dynamic Systems and Neural Control
14 other sections not shown
a-cuts adaptive adjusted analytically applications artificial neural network artificial neurons associated autoassociative neural network backpropagation called Cartesian product Chapter components compute connections consider control system crisp number crisp set defined defuzzification degree of fulfillment desired output equation evaluate example extension principle fuzzifying fuzzy algorithm fuzzy controller fuzzy logic fuzzy neuron fuzzy numbers fuzzy output fuzzy relations fuzzy set fuzzy systems fuzzy values given grade of membership Hebbian learning Hence hidden layer if/then rules implication operator implication relation input layer input pattern input vector interval involved Kohonen layer Larsen product linear linguistic variable mapping mathematical max-min composition membership function middle layer modus ponens obtain output layer output vector outstar pairs parameters pattern units perceptron PID controller problem represent representation result shown in Figure sigmoidal function signal square error summation Table theory tion training set universe of discourse valve weight vector Zadeh zero