1300 187 187
By the mid-1980s researchers from artificial intelligence, computer science, brain and cognitive science, and psychology realized that the idea of computers as intelligent machines was inappropriate. The brain does not run "programs"; it does something entirely different. But what? Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control our behavior, to ensure our survival. Researchers now agree that intelligence always manifests itself in behavior--thus it is behavior that we must understand. An exciting new field has grown around the study of behavior-based intelligence, also known as embodied cognitive science, "new AI," and "behavior-based AI." This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization, and learning, the authors derive a set of principles and a coherent framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building. The book includes all the background material required to understand the principles underlying intelligence, as well as enough detailed information on intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
" Understanding Intelligence is comprehensive and highly readable introduction to embodied cognitive science. It will be particularly helpful for people interested in getting involved in the construction of intelligent agents." Arthur B. Markman Science "People trained in classical AI will find this book an articulate and thought-provoking challenge to much that they have taken for granted. People new to cognitive science will find it a stimulating introduction to one of the field's most productive controversies. Pfeifer and Scheier deserve our thanks for a thorough, accessible, and courteous contribution in the best tradition of scholarly debate." H. Van Dyke Computing Reviews
| Preface | p. xi |
| The Study of Intelligence--Foundations and Issues | p. 1 |
| The Study of Intelligence | p. 3 |
| Characterizing Intelligence | p. 6 |
| Studying Intelligence: The Synthetic Approach | p. 21 |
| Foundations of Classical Artificial Intelligence and Cognitive Science | p. 35 |
| Cognitive Science: Preliminaries | p. 35 |
| The Cognitivistic Paradigm | p. 39 |
| An Architecture for an Intelligent Agent | p. 47 |
| The Fundamental Problems of Classical Al and Cognitive Science | p. 59 |
| Real Worlds versus Virtual Worlds | p. 59 |
| Some Well-Known Problems with Classical Systems | p. 63 |
| The Fundamental Problems of Classical Al | p. 64 |
| Remedies and Alternatives | p. 74 |
| A Framework for Embodied Cognitive Science | p. 79 |
| Embodied Cognitive Science: Basic Concepts | p. 81 |
| Complete Autonomous Agents | p. 82 |
| Biological and Artificial Agents | p. 99 |
| Designing for Emergence--Logic-Based and Embodied Systems | p. 111 |
| Explaining Behavior | p. 127 |
| Neural Networks for Adaptive Behavior | p. 139 |
| From Biological to Artificial Neural Networks | p. 140 |
| The Four or Five Basics | p. 143 |
| Distributed Adaptive Control | p. 152 |
| Types of Neural Networks | p. 167 |
| Beyond Information Processing: A Polemic Digression | p. 172 |
| Approaches and Agent Examples | p. 179 |
| Braitenberg Vehicles | p. 181 |
| Motivation | p. 181 |
| The Fourteen Vehicles | p. 182 |
| Segmentation of Behavior and the Extended Braitenberg Architecture | p. 195 |
| The Subsumption Architecture | p. 199 |
| Behavior-Based Robotics | p. 201 |
| Designing a Subsumption-Based Robot | p. 202 |
| Examples of Subsumption-Based Architectures | p. 206 |
| Conclusions: The Subsumption Approach to Designing Intelligent Systems | p. 219 |
| Artificial Evolution and Artificial Life | p. 227 |
| Basic Principles | p. 230 |
| An Introduction to Genetic Algorithms: Evolving a Neural Controller for an Autonomous Agent | p. 234 |
| Examples of Artificially Evolved Agents | p. 240 |
| Toward Biological Plausibility: Cell Growth from Genome-Based Cell-to-Cell Communication | p. 250 |
| Real Robots, Evolution of Hardware, and Simulation | p. 255 |
| Artificial Life: Additional Examples | p. 260 |
| Methodological Issues and Conclusions | p. 270 |
| Other Approaches | p. 277 |
| The Dynamical Systems Approach | p. 277 |
| Behavioral Economics | p. 283 |
| Schema-Based Approaches | p. 292 |
| Principles of Intelligent Systems | p. 297 |
| Design Principles of Autonomous Agents | p. 299 |
| The Nature of the Design Principles | p. 299 |
| Design Principles for Autonomous Agents | p. 302 |
| Design Principles in Context | p. 318 |
| The Principle of Parallel, Loosely Coupled Processes | p. 327 |
| Control Architectures for Autonomous Agents | p. 330 |
| Traditional Views on Control Architectures | p. 337 |
| Parallel, Decentralized Approaches | p. 345 |
| Case Study: A Self-Sufficient Garbage Collector | p. 357 |
| The Principle of Sensory-Motor Coordination | p. 377 |
| Categorization: Traditional Approaches | p. 378 |
| The Sensory-Motor Coordination Approach | p. 392 |
| Case Study: The SMC Agents | p. 407 |
| Application: Active Vision | p. 431 |
| The Principles of Cheap Design, Redundancy, and Ecological Balance | p. 435 |
| The Principle of Cheap Design | p. 435 |
| The Redundancy Principle | p. 446 |
| The Principle of Ecological Balance | p. 455 |
| The Value Principle | p. 467 |
| Value Systems | p. 469 |
| Self-Organization | p. 475 |
| Learning in Autonomous Agents | p. 485 |
| Human Memory: A Case Study | p. 503 |
| Memory Defined | p. 503 |
| Problems of Classical Notions of Memory | p. 506 |
| The Frame-of-Reference Problem in Memory Research | p. 511 |
| The Alternatives | p. 516 |
| Implications for Memory Research | p. 530 |
| Design and Evaluation | p. 535 |
| Agent Design Considerations | p. 537 |
| Preliminary Design Considerations | p. 539 |
| Agent Design | p. 542 |
| Putting It All Together: Control Architectures | p. 562 |
| Summary and a Fundamental Issue | p. 569 |
| Evaluation | p. 577 |
| General Introduction | p. 578 |
| Performing Agent Experiments | p. 588 |
| Measuring Behavior | p. 593 |
| Future Directions | p. 605 |
| Theory, Technology, and Applications | p. 607 |
| Hard Problems | p. 607 |
| Theory and Technology | p. 612 |
| Applications | p. 618 |
| Intelligence Revisited | p. 631 |
| Elements of a Theory of Intelligence | p. 631 |
| Implications for Society | p. 638 |
| Glossary | p. 645 |
| References | p. 659 |
| Author Index | p. 677 |
| Subject Index | p. 681 |
| Table of Contents provided by Syndetics. All Rights Reserved. |
ISBN: 9780262661256
ISBN-10: 026266125X
Series: Bradford Books
Audience:
Professional
For Ages: 22+ years old
Format:
Paperback
Language:
English
Number Of Pages: 700
Published: 3rd September 2001
Dimensions (cm): 25.3 x 18.0
x 3.249
Weight (kg): 1.254
9am - 4pm AEST, Monday - Friday
