Offering a new perspective, this book provides systematic design approaches for the identification, control, and recognition of nonlinear systems in uncertain environments. It introduces the concepts of deterministic learning theory and then discusses the persistent excitation property of RBF networks. The authors describe the theory of deterministic learning processes and address dynamical pattern recognition and pattern-based control processes. They present a new model of dynamical parallel distributed processing applicable to the detection and isolation of oscillation faults, ECG/EEG pattern recognition, robot learning and control, and security analysis and control of power systems.
Inhaltsverzeichnis
Introduction. RBF Networks and the PE Condition. Locally Accurate Identification of Nonlinear Systems. Learning from Closed-Loop Neural Control. Rapid Recognition of Dynamical Patterns. Deterministic Learning using Output Measurements. Applications of Deterministic Learning. Conclusions.