UID:
almafu_9959233116602883
Format:
1 online resource (423 p.)
ISBN:
1-281-03837-7
,
9786611038373
,
0-08-055135-1
Series Statement:
Neural network systems, techniques, and applications ; v. 2
Content:
Optimization Techniques is a unique reference source to a diverse array of methods for achieving optimization, and includes both systems structures and computational methods. The text devotes broad coverage toa unified view of optimal learning, orthogonal transformation techniques, sequential constructive techniques, fast back propagation algorithms, techniques for neural networks with nonstationary or dynamic outputs, applications to constraint satisfaction,optimization issues and techniques for unsupervised learning neural networks, optimum Cerebellar Model of Articulation Controller
Note:
Description based upon print version of record.
,
Front Cover; Optimization Techniques; Copyright Page; Contents; Contributors; Preface; Chapter 1. Optimal Learning in Artificial Neural Networks: A Theoretical View; I. Introduction; II. Formulation of Learning as an Optimization Problem; III. Learning with No Local Minima; IV. Learning with Suboptimal Solutions; V. Advanced Techniques for Optimal Learning; VI. Conclusions; References; Chapter 2. Orthogonal Transformation Techniques in the Optimization of Feedforward Neural Network Systems; I. Introduction; II. Mathematical Background for the Transformations Used
,
III. Network-Size Optimization through Subset SelectionIV. Introduction to Illustrative Examples; V. Example 1: Modeling of the Mackey-Glass Series; VI. Example 2: Modeling of the Sunspot Series; VII. Example 3: Modeling of the Rocket Engine Testing Problem; VIII. Assessment of Convergence in Training Using Singular Value Decomposition; IX. Conclusions; Appendix A: Configuration of a Series with Nearly Repeating Periodicity for Singular Value Decomposition-Based Analysis; Appendix B: Singular Value Ratio Spectrum; References; Chapter 3. Sequential Constructive Techniques; I. Introduction
,
II. Problems in Training with Back PropagationIII. Constructive Training Methods; IV. Sequential Constructive Methods: General Structure; V. Sequential Constructive Methods: Specific Approaches; VI. Hamming Clustering Procedure; VII. Experimental Results; VIII. Conclusions; References; Chapter 4. Fast Backpropagation Training Using Optimal Learning Rate and Momentum; I. Introduction; II. Computation of Derivatives of Learning Parameters; III. Optimization of Dynamic Learning Rate; IV. Simultaneous Optimization of μ and a; V. Selection of the Descent Direction; VI. Simulation Results
,
VII. ConclusionReferences; Chapter 5. Learning of Nonstationary Processes; I. Introduction; II. A Priori Limitations; III. Formalization of the Problem; IV. Transformation into an Unconstrained Minimization Problem; V. One-to-One Mapping D; VI. Learning with Minimal Degradation Algorithm; VII. Adaptation of Learning with Minimal Degradation for Radial Basis Function Units; VIII. Choosing the Coefficients of the Cost Function; IX. Implementation Details; X. Performance Measures; XI. Experimental Results; XII. Discussion; XIII. Conclusion; References; Chapter 6. Constraint Satisfaction Problems
,
I. Constraint Satisfaction ProblemsII. Assessment Criteria for Constraint Satisfaction Techniques; III. Constraint Satisfaction Techniques; IV. Neural Networks for Constraint Satisfaction; V. Assessment; References; Chapter 7. Dominant Neuron Techniques; I. Introduction; II. Continuous Winner-Take-All Neural Networks; III. Iterative Winner-Take-All Neural Networks; IV. K-Winners-Take-All Neural Networks; V. Conclusions; References; Chapter 8. CMAC-Based Techniques for Adaptive Learning Control; I. Introduction; II. Neural Networks for Learning Control
,
III. Conventional Cerebellar Model Articulation Controller
,
English
Additional Edition:
ISBN 0-12-443862-8
Language:
English
