| Description |
xiv, 431 pages : illustrations ; 24 cm + 1 computer disk (3 1/2 in.) |
| Contents |
1. Deterministic Optimization -- 2. Stochastic Optimization -- 3. Hybrid Training Algorithms -- 4. Probabilistic Neural Networks I: Introduction -- 5. Probabilistic Neural Networks II: Advanced Techniques -- 6. Generalized Regression -- 7. The Gram-Charlier Neural Network -- 8. Dimension Reduction and Orthogonalization -- 9. Assessing Generalization Ability -- 10. Using the PNN Program |
| Summary |
This practical guide contains a wide variety of state-of-the-art algorithms that are useful in the design and implementation of neural networks. All algorithms are presented on both an intuitive and a theoretical level, with complete source code provided on an accompanying disk. Several training algorithms for multiple-layer feedforward networks (MLFN) are featured. The probabilistic neural network is extended to allow separate sigmas for each variable, and even separate sigma vectors for each class. The generalized regression neural network is similarly extended, and a fast second-order training algorithm for all of these models is provided. The book also discusses the recently developed Gram-Charlier neural network and provides important information on its strengths and weaknesses. Readers are shown several proven methods for reducing the dimensionality of the input data |
| Notes |
Accompanied by one 3 1/2 in. computer disk at Loans Counter at H 005.133 C111.1 MAS.A |
| Bibliography |
Includes bibliographical references (pages [407]-425) and index |
| Notes |
System requirements for accompanying computer disk: C++ |
| Subject |
C (Computer program language)
|
|
C++ (Computer program language)
|
|
Computer algorithms.
|
|
Neural networks (Computer science)
|
|
Statistics -- Computer programs.
|
| LC no. |
94043390 |
| ISBN |
0471105880 (paperback) |
|
