Naturally Intelligent Systems
by Caudill, Maureen; Butler, CharlesFormat: Paperback
Pub. Date: 1992-09-08
Publisher(s): Bradford Books
Other versions by this Author
List Price: $32.41
Buy New
Usually Ships in 8 - 10 Business Days.
$30.87
Rent Textbook
Select for Price
Used Textbook
We're Sorry
Sold Out
eTextbook
We're Sorry
Not Available
How Marketplace Works:
- This item is offered by an independent seller and not shipped from our warehouse
- Item details like edition and cover design may differ from our description; see seller's comments before ordering.
- Sellers much confirm and ship within two business days; otherwise, the order will be cancelled and refunded.
- Marketplace purchases cannot be returned to eCampus.com. Contact the seller directly for inquiries; if no response within two days, contact customer service.
- Additional shipping costs apply to Marketplace purchases. Review shipping costs at checkout.
Summary
For centuries, people have been fascinated by the possibility of building an artificial system that behaves intelligently. Now there is a new entry in this arena - neural networks. Naturally Intelligent Systems offers a comprehensive introduction to these exciting systems. It provides a technically accurate, yet down-to-earth discussion of neural networks, clearly explaining the underlying concepts of key neural network designs, how they are trained, and why they work. Throughout, the authors present actual applications that illustrate neural networks' utility in the new world. Maureen Caudill is a consultant based in San Diego, and author of the popular "Neural Network Primer" articles in AI Expert. Charles Butler is a Principal Research Scientist at Physical Sciences Inc. in Alexandria, Virginia.
Table of Contents
| Acknowledgments | |
| Natural Intelligence | |
| Neural Networks in a Nutshell | |
| Characteristics of Neural Networks | |
| Comparing a Neural Network to a Digital Computer | |
| Building Blocks of Neural Networks | |
| The Anatomy of a Neurode | |
| The Network in Action | |
| Implementation: The Artificial Retina | |
| Neural Networks and Other System | |
| Neural Networks and Artificial Intelligence | |
| Neural Networks and Parallel Computers | |
| Do Neurodes Have Internal Memory? | |
| Relationship to Analog Computers | |
| Associative Memories | |
| Features of Associative Memories | |
| Classes of Neural Network Associative Memories | |
| Using an Associative Memory | |
| Neural Network Models | |
| Crossbar Associative Memories | |
| Energy Surface Representation | |
| Matrix Representation of Crossbar Networks | |
| Feedback Competition Representation | |
| An Illustrative Example | |
| The Problems with Crossbar Networks | |
| Then Why Study the Crossbar? | |
| Adaptive Filter Associative Memories | |
| Introducing the Adaline | |
| Geometry of the Delta Rule | |
| Choosing the Learning Constant | |
| What Can the Adaline Do? | |
| Limitations of the Adaline | |
| Training the Madaline | |
| Higher-Order Networks | |
| The Polynomial Adaline | |
| Application: The Vectorcardiograph | |
| Competitive Filter Associative Memories | |
| A Self-Organizing Architecture | |
| Lateral Inhibition | |
| The Network in Operation | |
| The Geometry of the Network | |
| The Crust Thickens | |
| Training Techniques | |
| The Topology-Preserving Map | |
| Application: The Voice Typewriter | |
| Learning | |
| Types of Learning | |
| Memory | |
| Learning and Memory in Neural Networks | |
| Training a Neural Network | |
| Hebbian Learning | |
| Neohebbian Learning | |
| Differential Hebbian Learning | |
| Classical, Conditioning | |
| Classical or Pavlovian Conditioning | |
| The Instar and Outstar | |
| Outstar Learning | |
| Outstar Inconsistencies | |
| Drive-Reinforcement Theory | |
| Learning Sequences of Patterns | |
| The Music Box Associative Memory | |
| Single-Neurode Systems | |
| The Outstar Avalanche | |
| Recognizing Sequences of Patterns | |
| Autonomous Learning | |
| Characteristics of Autonomous Learning Systems | |
| Recall by Association | |
| Seek and Ye Shall Find | |
| Dealing with Reality | |
| The Importance of Being Significant | |
| On with the New, On with the Old | |
| Categorically Speaking | |
| The Memory Shell Game | |
| Elementary, My Dear Watson | |
| An Ocean of Experience | |
| Autonomous Learning Redux | |
| A Classic System: The Perceptron | |
| Hierarchical Systems | |
| Linear Separability | |
| Kolmogorov's Theorem | |
| What Kolmogorov Didn't Say | |
| Application: The Neocognitron | |
| Backpropagation Networks | |
| Features of Backpropagation Systems | |
| Building a Backpropagation System | |
| The Backpropagation Process | |
| Limitations of Backpropagation Networks | |
| Variations of the Generalized Delta Rule | |
| Scaling Problems | |
| Biological Arguments against Backpropagation | |
| Applications of Backpropagation Systems | |
| Application: NETtalk | |
| Hybrid Networks | |
| The Counterpropagation Network | |
| Training Techniques and Problems | |
| The Size of the Middle Layer | |
| Using the Counterpropagation Network | |
| Adaptive Resonance Networks | |
| The Principle of Adaptive Resonance | |
| Operation of the ART 1 Network | |
| The Reset Subsystem | |
| The Gain Control Subsystem and the 2/3 Rule | |
| Troubles with ART 1 | |
| Art 2 | |
| Grandmother Nodes and ART | |
| The Limitations of ART Networks in General | |
| Neural Network Implementations | |
| Software Simulations | |
| Neurocomputers | |
| Networks in Hardware | |
| Optical Neural Networks | |
| Neural Network | |
| An Expert Mortgage Insurance Underwriter | |
| A Process Controller That the Freeway | |
| A Robotic Arm | |
| Sonar Signal Processing | |
| A Look Ahead | |
| Implementations Development | |
| Weird Science | |
| Neural Network Theory | |
| Applications | |
| A Final Word | |
| Glossary | |
| Index | |
| Table of Contents provided by Publisher. All Rights Reserved. |
An electronic version of this book is available through VitalSource.
This book is viewable on PC, Mac, iPhone, iPad, iPod Touch, and most smartphones.
By purchasing, you will be able to view this book online, as well as download it, for the chosen number of days.
Digital License
You are licensing a digital product for a set duration. Durations are set forth in the product description, with "Lifetime" typically meaning five (5) years of online access and permanent download to a supported device. All licenses are non-transferable.
More details can be found here.
A downloadable version of this book is available through the eCampus Reader or compatible Adobe readers.
Applications are available on iOS, Android, PC, Mac, and Windows Mobile platforms.
Please view the compatibility matrix prior to purchase.