A practical guide to neural nets
著者
書誌事項
A practical guide to neural nets
Addison-Wesley, c1991
大学図書館所蔵 件 / 全2件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Includes bibliographical references and index
内容説明・目次
内容説明
Have neural networks emerged from research? Is this the time to develop applications?
A Practical Guide To Neural Nets is a quick, thorough introduction for technical professionals and managers. Among other issues it addresses:
- Which applications are appropriate for neural nets
- Why this is not traditional programming, but a totally new paradigm
- Why this new paradigm may provide efficient solutions for your technical problems.
This timely book explains the current state of the art, with examples, from research to developing systems to deployed applications. You'll learn how neural nets function, and how to move from theory to application, as summarized in this flow chart for development of a neural network to be embedded in an expert system.
Marilyn McCord Nelson was formerly at Texas Instruments, where she designed and developed real-time software and was an instructor in artificial intelligence. W.T. Illingworth was formerly a Member of the Technical Staff and Manager of Intelligent Systems in Texas Instruments' Defense Systems and Electronics Group in Dallas, where he was responsible for implementing new concepts, including neural networks.
目次
List of Illustrations.
Acknowledgments.
Preface.
1. What Can You Do with a Neural Network?
Introduction.
Existing Applications.
Prototype and Research Activity.
List of Possible Applications.
Summary.
2. Next Question: What and Why?
What Is a Neural Network?
Why Neural Networks Now?
Summary.
3. A Brief History of Neural Networks.
Conception.
Gestation.
Birth.
Early Infancy.
Stunted Growth.
Late Infancy.
Who Are the Key Players?
Summary.
4. How Do Neural Networks Work?
Anthropomorphism: The Biological Metaphor.
The Basic Components.
Summary.
5. What Are Neural Networks Like?
Mathematical Basis.
Inherent Parallelism.
Storing Knowledge.
Fault Tolerance.
Adaptability.
Pattern Recognition.
Appropriate Tasks.
Types of Problems Addressed.
Limitations and Concerns.
Other Concerns.
Summary.
6. How Do Neural Networks Relate to Other Technologies?
Statistical Methods.
Artificial Intelligence.
Whole Brain Approach.
Hybrid Technologies.
Summary: A Maturation.
7. How Many Ways Can You Organize a Neural Network?
Neurodynamics.
Architecture.
What Are Some of the Neural Network Paradigms?
Summary.
8. How Do Neural Networks Learn?
The Basic Learning Mechanism.
Learning Modes.
Learning Laws.
Architecture and Learning Paradigms.
Research Areas.
Summary.
9. How Do You Move from Theory to Applications?
Getting Started: One Approach.
Preparing the Network Data.
Five Network Applications on a PC.
Comparing Network Applications.
Back Propagation Mathematics: How to Computer a Neural Network Manually.
Implementing Your Network.
Summary and Recommendations.
10. How Are Neural Networks Being Implemented?
Introduction.
Terminology.
Software Simulations.
Emulation within Parallel Architecture.
Neurocomputers.
Networks on a Chip.
Optical Neural Networks.
Biological Computers.
Synergistic Efforts.
Summary.
11. What Is the Current Research?
Introduction.
Issues and Problems.
Emerging Directions.
Summary.
12. Where Do We Go from Here?
Introduction.
Are Neural Networks Intelligent?
Why Use Neural Nets?
New Horizons.
Concerns.
Summary and Opinions.
Afterword.
Appendix A. Your Interactive Neural Network Disk.
Appendix B. Bibliography and Reading List.
Appendix C. Selected Mathematics.
Appendix D. Simulation of a Processing Element on Lotus 1-2-3.
Index. 0201633787T04062001
「Nielsen BookData」 より