Cargando…
Practical neural network recipes in C++ /
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 pr...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Boston :
Morgan Kaufmann,
[1993]
|
| Temas: | |
| Acceso en línea: | Texto completo (Requiere registro previo con correo institucional) |
Tabla de Contenidos:
- Front Cover; Practical Neural Network Recipes in C++; Copyright Page; Dedication; Table of Contents; Preface; Chapter 1. Foundations; Motivation; New Life for Old Techniques; Perceptrons and Linear Separability; Neural Network Capabilities; Basic Structure of a Neural Network; Training; Validation; Chapter 2. Classification; Binary Decisions; Multiple Classes; Supervised versus Unsupervised Training; Chapter 3. Autoassociation; Autoassociative Filtering; Noise Reduction; Learning a Prototype from Exemplars; Exposing Isolated Events; Pattern Completion; Error Correction; Data Compression.
- Chapter 4. Time-Series PredictionThe Basic Model; Input Data; Multiple Prediction; Multiple Predictors; Measuring Prediction Error; Chapter 5. Function Approximation; Univariate Function Approximation; Inverse Modeling; Multiple Regression; Chapter 6. Multilayer Feedforward Networks; Basic Architecture; Theoretical Discussion; Algorithms for Executing the Network; Training the Network; Training by Backpropagation of Errors; Training by Conjugate Gradients; Eluding Local Minima in Learning; When to Use a Multiple-Layer Feedforward Network; Chapter 7. Eluding Local Minima I: Simulated Annealing.
- OverviewChoosing the Annealing Parameters; Implementation in Feedforward Network Learning; A Sample Program; A Sample Function; Random Number Generation; Going on from Here; Chapter 8. Eluding Local Minima II: Genetic Optimization; Overview; Designing the Genetic Structure; Evaluation; Parent Selection; Reproduction; Mutation; A Genetic Minimization Subroutine; Some Functions for Genetic Optimization; Advanced Topics in Genetic Optimization; Chapter 9. Regression and Neural Networks; Overview; Singular-Value Decomposition; Regression in Neural Networks.
- Chapter 10. Designing Feedforward Network ArchitecturesHow Many Hidden Layers?; How Many Hidden Neurons?; How Long Do I Train This Thing???; Chapter 11. Interpreting Weights: How Does This Thing Work?; Features Used by Networks in General; Features Used by a Particular Network; Chapter 12. Probabilistic Neural Networks; Overview; Computational Aspects; Optimizing Sigma; A Sample Program; Bayesian Confidence Measures; Autoassociative Versions; When to Use a Probabilistic Neural Network; Chapter 13. Functional Link Networks; Application to Nonlinear Approximation.
- Mathematics of the Functional Link NetworkWhen to Use a Functional Link Network; Chapter 14. Hybrid Networks; Functional Link Net as a Hidden Layer; Fast Bayesian Confidences; Attention-based Processing; Factorable Problems; Chapter 15. Designing the Training Set; Number of Samples; Borderline Cases; Hidden Bias; Balancing the Classes; Fudging Cases; Chapter 16. Preparing Input Data; General Considerations; Types of Measurements; Is Scaling Always Necessary?; Transformations; Circular Discontinuity; Outliers; Missing Data; Chapter 17. Fuzzy Data and Processing.