Practical Neural Network Recipies in C++

Masters

• Publisher: Morgan Kaufmann
• Year: 2014
• ISBN:
  9780080514338
• Topic: Computer Science
• Subtopic: Computer Science General
• Index: Computer Science

This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assumed and all models are presented from the ground up.The principle focus of the book is the three layer feedforward network, for more than a decade as the workhorse of professional arsenals. Other network models with strong performance records are also included.Bound in the book is an IBM diskette that includes the source code for all programs in the book. Much of this code can be easily adapted to C compilers. In addition, the operation of all programs is thoroughly discussed both in the text and in the comments within the code to facilitate translation to other languages.

Table of contents

• Front Cover
• Practical Neural Network Recipes in C++
• Copyright Page
• Table of Contents
• Dedication
• Preface
• Chapter 1. Foundations
• Chapter 2. Classification
• Chapter 3. Autoassociation
• Chapter 4. Time-Series Prediction
• Chapter 5. Function Approximation
• Chapter 6. Multilayer Feedforward Networks
• Chapter 7. Eluding Local Minima I: Simulated Annealing
• Chapter 8. Eluding Local Minima II: Genetic Optimization
• Chapter 9. Regression and Neural Networks
• Chapter 10. Designing Feedforward Network Architectures
• Chapter 11. Interpreting Weights: How Does This Thing Work?
• Chapter 12. Probabilistic Neural Networks
• Chapter 13. Functional Link Networks
• Chapter 14. Hybrid Networks
• Chapter 15. Designing the Training Set
• Chapter 16. Preparing Input Data
• Chapter 17. Fuzzy Data and Processing
• Chapter 18. Unsupervised Training
• Chapter 19. Evaluating Performance of Neural Networks
• Chapter 20. Confidence Measures
• Chapter 21. Optimizing the Decision Threshold
• Chapter 22. Using the NEURAL Program
• Appendix
• Bibliography
• Index