Artificial neural systems : principles and practice.

FOREWORD ; PREFACE ; Principles ; Neurons ; A BIOLOGICAL NEURON; Synaptic Transmission; TRANSMISSION ACROSS SYNAPSES; AN ARTIFICIAL NEURON; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Basic Neurons ; INTEGRATE-AND-FIRE NEURON; PROBABILITY; STEIN MODEL OF NEURON; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Basic Fuzzy Neuron and Fundamentals of ANN ; A FUZZY NEURON; The Fuzzy-logic Neuron; PRINCIPLES OF ARTIFICIAL NEURAL NETWORK ANALYSIS AND DESIGN; The Wave Neural Networks; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Fundamental Algorithms and Methods.

INTRODUCTIONDENSITY BASED ALGORITHMS: CLUSTERING ALGORITHMS; NATURE-BASED ALGORITHMS; Evolutionary Algorithm and Programming ; Genetic Algorithm; GA Operators; APPLICATIONS OF GENETIC ALGORITHM; NETWORK METHOD: EDGES AND NODES; MULTI-LAYERED PERCEPTRON; REAL-TIME APPLICATIONS OF STATE-OF-THE-ART ANN SYSTEMS; DEFINITION OF ARTIFICIAL NEURAL NETWORKS (ANN); Intelligence; An Artificial Neural Network (ANN) system; PERFORMANCE MEASURES; Receiver's Operating Characteristics (ROC); Hypothesis Testing; Chi-squared (Goodness-of-fit) Test; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES.

Quantum Logic and Classical Connectivity INTRODUCTION; QUANTUM LOGIC AND QUANTUM MATHEMATICS; Quantum Gates (Primitives); Quantum Algebra; QUANTUM NEURAL NETWORK; CLASSICAL PRIMITIVES AND WEIGHTS; Memristance; HODGKIN-HUXLEY NEURON; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Practices ; Learning Methods ; INTRODUCTION; THE ADAPTIVE LINEAR NEURON (ADALINE); THE RECURSIVE-LEAST-SQUARE (RLS) ALGORITHM; MULTI-AGENT NETWORK; NEUROMORPHIC NETWORK; BAYESIAN NETWORKS; Gaussian Mixture Model; K-means; Radial Basis Function (RBF); Generative Topographic Mapping (GTM); NEURO-FUZZY SYSTEM.

RESEARCH AND APPLICATIONS OF ANN SYSTEMSCONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Neural Networks ; INTRODUCTION; WEIGHTLESS NETWORKS; Probabilistic Convergent Network (PCN); PCN Network Architecture; Learning or Training; Recognition or Classification; THE ENHANCED PROBABILISTIC CONVERGENT NETWORK (EPCN); THE EPCN; Recognition procedure; The EPCN Software Implementation; A WEIGHTED NETWORK ; Multi-Layer Perceptron (MLP); Industrial Applications of MLP; BAYESIAN NETWORKS; Mixture Density Network (MDN); Helmholtz Machine; THE DYNAMICS AND EVALUATION OF ANN SYSTEMS.

Introduction: Chi-Squared Probability Density FunctionThe Dynamics; Fusion; Generalized Likelihood Ratio Test (GLRT); GLRT Procedure:; Wald Test; Wald Test Procedure:; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Selection and Combination Strategy of ANN Systems ; INTRODUCTION; FACTORIAL SELECTION; Comparison to Other Similar Coding Scheme for Multi-class Problems; THE GROUP METHOD OF SELECTION; Topology of GMDH; Applications of GMDH; CONFLICT OF INTEREST; ACKNOWLEDGEMENTS; REFERENCES; Probability-based Neural Network Systems ; INTRODUCTION; RANDOM-NUMBER GENERATORS; MARKOV CHAIN.

Includes bibliographical references and index.

Annotation An intelligent system is one which exhibits characteristics including, but not limited to, learning, adaptation, and problem-solving. Artificial Neural Network (ANN) Systems are intelligent systems designed on the basis of statistical models of learning that mimic biological systems such as the human central nervous system. Such ANN systems represent the theme of this book. This book also describes concepts related to evolutionary methods, clustering algorithms, and others networks which are complementary to ANN system. The book is divided into two parts. The first part explains basic concepts derived from the natural biological neuron and introduces purely scientific frameworks used to develop a viable ANN model. The second part expands over to the design, analysis, performance assessment, and testing of ANN models. Concepts such as Bayesian networks, multi-classifiers, and neuromorphic ANN systems are explained, among others. Artificial Neural Systems: Principles and Practice takes a developmental perspective on the subject of ANN systems, making it a beneficial resource for students undertaking graduate courses and research projects, and working professionals (engineers, software developers) in the field of intelligent systems design.

eBooks on EBSCOhost EBSCO eBook Subscription Academic Collection - Worldwide