Static and Dynamic Neural Networks : From Fundamentals to Advanced Theory
Madan M. Gupta
Bok Engelsk 2004 · Electronic books.
| Annen tittel | |
|---|---|
| Utgitt | Hoboken : : Wiley, , 2004.
|
| Omfang | 1 online resource (751 p.)
|
| Opplysninger | Description based upon print version of record.. - Contents; Foreword; Preface; Acknowledgments; PART I: FOUNDATIONS OF NEURAL NETWORKS; 1 Neural Systems: An Introduction; 1.1 Basics of Neuronal Morphology; 1.2 The Neuron; 1.3 Neurocomputational Systems: Some Perspectives; 1.4 Neuronal Learning; 1.5 Theory of Neuronal Approximations; 1.6 Fuzzy Neural Systems; 1.7 Applications of Neural Networks: Present and Future; 1.7.1 Neurovision Systems; 1.7.2 Neurocontrol Systems; 1.7.3 Neural Hardware Implementations; 1.7.4 Some Future Perspectives; 1.8 An Overview of the Book; 2 Biological Foundations of Neuronal Morphology. - 2.1 Morphology of Biological Neurons2.1.1 Basic Neuronal Structure; 2.1.2 Neural Electrical Signals; 2.2 Neural Information Processing; 2.2.1 Neural Mathematical Operations; 2.2.2 Sensorimotor Feedback Structure; 2.2.3 Dynamic Characteristics; 2.3 Human Memory Systems; 2.3.1 Types of Human Memory; 2.3.2 Features of Short-Term and Long-Term Memories; 2.3.3 Content-Addressable and Associative Memory; 2.4 Human Learning and Adaptation; 2.4.1 Types of Human Learning; 2.4.2 Supervised and Unsupervised Learning Mechanisms; 2.5 Concluding Remarks; 2.6 Some Biological Keywords; Problems. - 3 Neural Units: Concepts, Models, and Learning3.1 Neurons and Threshold Logic: Some Basic Concepts; 3.1.1 Some Basic Binary Logical Operations; 3.1.2 Neural Models for Threshold Logics; 3.2 Neural Threshold Logic Synthesis; 3.2.1 Realization of Switching Function; 3.3 Adaptation and Learning for Neural Threshold Elements; 3.3.1 Concept of Parameter Adaptation; 3.3.2 The Perceptron Rule of Adaptation; 3.3.3 Mays Rule of Adaptation; 3.4 Adaptive Linear Element (Adaline); 3.4.1 α-LMS (Least Mean Square) Algorithm; 3.4.2 Mean Square Error Method; 3.5 Adaline with Sigmoidal Functions. - 3.5.1 Nonlinear Sigmoidal Functions3.5.2 Backpropagation for the Sigmoid Adaline; 3.6 Networks with Multiple Neurons; 3.6.1 A Simple Network with Three Neurons; 3.6.2 Error Backpropagation Learning; 3.7 Concluding Remarks; Problems; PART II: STATIC NEURAL NETWORKS; 4 Multilayered Feedforward Neural Networks (MFNNs) and Backpropagation Learning Algorithms; 4.1 Two-Layered Neural Networks; 4.1.1 Structure and Operation Equations; 4.1.2 Generalized Delta Rule; 4.1.3 Network with Linear Output Units; 4.2 Example 4.1: XOR Neural Network; 4.2.1 Network Model; 4.2.2 Simulation Results. - 4.2.3 Geometric Explanation4.3 Backpropagation (BP) Algorithms for MFNN; 4.3.1 General Neural Structure for MFNNs; 4.3.2 Extension of the Generalized Delta Rule to General MFNN Structures; 4.4 Deriving BP Algorithm Using Variational Principle; 4.4.1 Optimality Conditions; 4.4.2 Weight Updating; 4.4.3 Transforming the Parameter Space; 4.5 Momentum BP Algorithm; 4.5.1 Modified Increment Formulation; 4.5.2 Effect of Momentum Term; 4.6 A Summary of BP Learning Algorithm; 4.6.1 Updating Procedure; 4.6.2 Signal Propagation in MFNN Architecture; 4.7 Some Issues in BP Learning Algorithm. - 4.7.1 Initial Values of Weights and Learning Rate. - Provides comprehensive treatment of the theory of both static and dynamic neural networks.* Theoretical concepts are illustrated by reference to practical examples Includes end-of-chapter exercises and end-of-chapter exercises.*An Instructor Support FTP site is available from the Wiley editorial department.
|
| Emner | |
| Sjanger | |
| Dewey | |
| ISBN | 0471219487
|
