Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine IntelligenceWritten by one of the foremost experts in the field of neural networks, this is the first book to combine the theories and applications or neural networks and fuzzy systems. The book is divided into three sections: Neural Network Theory, Neural Network Applications, and Fuzzy Theory and Applications. It describes how neural networks can be used in applications such as: signal and image processing, function estimation, robotics and control, analog VLSI and optical hardware design; and concludes with a presentation of the new geometric theory of fuzzy sets, systems, and associative memories. |
Contents
ACTIVATIONS AND SIGNALS | 39 |
Common Signal Functions | 48 |
Neuronal Dynamical Systems | 55 |
Copyright | |
26 other sections not shown
Common terms and phrases
A₁ ABAM activation adaptive algorithm antecedent approximation associative memory Azimuth B₁ backpropagation behavior binary BIOFAM bipolar bivalent centroid clustering competitive learning compute control surface convergence correlation-minimum correlation-product corresponds defines defuzzification degree denotes differential competitive learning dynamical system encoding equals equations equilibrium error estimate FAM bank FAM cells FAM matrix FAM rules FAM system FAM-rule feedforward Figure fit value fit vector fuzzy association fuzzy controller fuzzy sets fuzzy subsets fuzzy systems fuzzy variables fuzzy-set values global Grossberg Hebbian learning hyperrectangle inference input input-output iteration Kalman filter Kosko linear Lyapunov function maps menu neural networks neurons noise nonfuzzy nonlinear option output fuzzy set parameters pattern pendulum positive probability problems product space pulse quantization RABAM random variables represent signal functions steady-state FAM stochastic subimage subsethood synaptic vectors theorem theory threshold trajectories truck truck-and-trailer universe of discourse unsupervised learning velocity weight zero