Diagrammatic reasoning—the understanding of concepts and ideas by the use of diagrams and imagery, as opposed to linguistic or algebraic representations—not only allows us to gain insight into the way we think, but is a potential base for constructing representations of diagrammatic information that can be stored and processed by computers.
Diagrammatic Reasoning brings together recent investigations into the cognitive, the logical, and particularly the computational characteristics of diagrammatic representations and the reasoning that can be done with them. Following a foreword by Herbert Simon and an introduction by the editors, twenty-seven chapters provide an overview of the recent history of the subject, survey and extend the underlying theory of diagrammatic representation, and provide numerous examples of diagrammatic reasoning (human and mechanical) that illustrate both its powers and its limitations.
Each of the book's four sections (Historical and Philosophical Background, Theoretical Foundations, Cognitive and Computational Models, and Problem Solving with Diagrams) begins with an introduction by an eminent researcher. These introductions provide interesting personal perspectives as well as place the work in the proper context.
Computation and Intelligence brings together 29 readings in Artificial Intelligence that are particularly relevant to today's student/practitioner. With its helpful critique of the selections, extensive bibliography, and clear presentation of the material, Computation and Intelligence will be a useful adjunct to any course in AI as well as a handy reference for professionals in the field.
The book is divided into five parts, each reflecting the stages of development of AI. The first part, Foundations,, contains readings that present or discuss foundational ideas linking computation and intelligence, typified by A. M. Turing's "Computing Machinery and Intelligence." The second part, Knowledge Representation, presents a sampling of numerous representational schemes by Newell, Minsky, Collins & Quillian, Winograd, Schank, Hayes, Holland, McClelland, Rumelhart, Hinton, and Brooks.
The third part, Weak Method Problem Solving, fouses on the research and design of syntax-based problem solvers, including the most famous of these, the Logic Theorist and GPS. The fourth part, Reasoning in Complex and Dynamic Environments, presents a broad spectrum of the AI community's research in knowledge-intensive problem solving, from McCarthy's early design of systems with "common sense" to model-based reasoning.
The two concluding selections, by Marvin Minsky and by Herbert Simon, respectively, present the recent thoughts of two of AI's pioneers who revisit the concepts and controversies that have developed during the evolution of the tools and techniques that make up the current practice of Artificial Intelligence.
The first international conference on multiagent systems is organized as a joint effort of the North American Distributed Artificial Intelligence community, the Japanese Multiagent and Cooperative Computing community, and the European Modeling Autonomous Agents in a Multiagent World community, with support from AAAI and sanctioned by ECCAI. The Proceedings cover a broad spectrum of perspectives including artificial life, communications issues, and negotiation strategies.
- Agent Architectures.
- Artificial Life (from a multiagent perspective).
- Believable Agents.
- Cooperation, Coordination, and Conflict.
- Communcation Issues.
- Conceptual and Theoretical Foundations of Multiagent Systems.
- Development and Engineering Methodologies.
- Distributed Artificial Intelligence.
- Distributed Consensus and Algorithms for Multiagent Interaction.
- Distributed Search.
- Evaluation of Multiagent Systems.
- Integrated Testbeds and Development Environments.
- Intelligent Agents in Enterprise Integration Systems and Similar Types of Applications.
- Learning and Adaptation in Multiagent Systems.
- Multiagent Cooperative Reasoning from Distributed Heterogeneous Databases.
- Multiagent Planning and Planning for Multiagent Worlds.
- Negotiation Strategies (in both competitive and cooperative situations).
- Organization, Organizational Knowledge, and Organization Self-Design.
- Practical Applications of Multiagent Systems (enterprises, robotics, sensing, manufacturing).
- Resource Allocation in Multiagent Systems.
- Social Structures and their Signfiicance in Multiagent Systems.
The increased sophistication and availability of massively parallel supercomputers has had two major impacts on research in artificial intelligence, both of which are addressed in this collection of exciting new AI theories and experiments. Massively parallel computers have been used to push forward research in traditional AI topics such as vision, search, and speech. More important, these machines allow AI to expand in exciting new ways by taking advantage of research in neuroscience and developing new models and paradigms, among them associate memory, neural networks, genetic algorithms, artificial life, society-of-mind models, and subsumption architectures.
A number of chapters show that massively parallel computing enables AI researchers to handle significantly larger amounts of data in real time, which changes the way that AI systems can be built, which in turn makes memory-based reasoning and neural-network-based vision systems become practical. Other chapters present the contrasting view that massively parallel computing provides a platform to model and build intelligent systems by simulating the (massively parallel) processes that occur in nature.
AAAI proceedings describe innovative concepts, techniques, perspectives, and observations that present promising research directions in artificial intelligence.
Topics include: The principles underlying cognition, perception, and action in humans' and machines. The design, application, and evaluation of AI algorithms and intelligent systems. The analysis of tasks and domains in which intelligent systems perform.
This collection of original contributions reports on key advances in intelligent (knowledge-based) user interfaces that exploit multiple media - text, graphics, maps - and multiple modalities - visual, auditory, gestural - to facilitate human-computer interaction. Chapters are grouped into three sections that address automated presentation design, intelligent multimedia interfaces, and architectural and theoretical issues.
Although humans have a natural facility for managing and exploiting multiple input and output media, computers do not. Consequently, providing machines with the ability to interpret multimedia input and generate multimedia output would be a valuable facility for a number of key applications such as information retrieval and analysis, training and decision support. Successful intelligent multimedia interfaces require theories and technologies from a host of disciplines, including computational linguistics, computer graphics, cognitive science, human computer interaction, and computer-supported cooperative work - all of them represented in this collection.
Mark T. Maybury is Director of the Bedford Artificial Intelligence Center and Associate Department Head of Advanced Information Systems Technology at The MITRE Corporation.
The enormous amount of data generated by the Human Genome Project and other large-scale biological research has created a rich and challenging domain for research in artificial intelligence. These original contributions provide a current sampling of AI approaches to problems of biological significance; they are the first to treat the computational needs of the biology community hand-in-hand with appropriate advances in artificial intelligence. Focusing on novel technologies and approaches, rather than on proven applications, they cover genetic sequence analysis, protein structure representation and prediction, automated data analysis aids, and simulation of biological systems. A brief introductory primer on molecular biology and Al gives computer scientists sufficient background to understand much of the biology discussed in the book.
The past decade has seen considerable advances in CAE tools that employ leading-edge artificial intelligence techniques and that can be used with CAD/CAM tools to reduce design costs. In three parts, this book covers current Al applications that can prove beneficial in the design and planning stages of manufacturing, that can assist in solving scheduling and control problems, and that can be used in manufacturing integration.
Contents: Application of Machine Learning to Industrial Planning and Decision Making. Incorporating Special Purpose Resource Design in Planning to Make More Efficient Plans. Geometric Reasoning Using a Feature Algebra. Backward Assembly Planning Symmetry Groups in Solid Model-Based Assembly Planning. An Expert System Approach for Economic Evaluation of Machining Operation Planning. Interactive Problem Solving for Production Planning. An Abstraction-Based Search and Learning Approach for Effective Scheduling. ADDYMS: Architecture for Distributed Dynamic Manufacturing Scheduling. An Architecture for Real Time Distributed Scheduling. Teamwork Among Intelligent Agents: Framework and Case Study in Robotic Service. Exploiting Local Flexibility During Execution of Precomputed Schedules. Symbolic Representation and Planning for Robot Control Systems in Manufacturing. An Architecture for Integrating Enterprise Automation. An Intelligent Agent Framework for Enterprise Integration. Integrated Software System for Intelligent Manufacturing. Enterprise Management Network Architecture: A Tool for Manufacturing Enterprise Integration. Design and Manufacturing: Integration through Quality.
This anthology provides an informative and timely introduction to ongoing research on music as a cognitive process, bringing a new coherence to the emerging science of musical activity.
Following the foreword, which is based on a conversation with Marvin Minsky, 26 contributions explore musical composition, analysis, performance, perception, and learning and tutoring. Their goal is to discover how these activities can be interpreted, understood, modeled, and supported through the use of computer programs. Each chapter is put into perspective by the editors, and empirical investigations are framed by a discussion of the nature of cognitive musicology and of epistemological problems of modeling musical action.
The contributions, drawn from two international workshops on AI and Music held in 1988 and 1989, are grouped in seven sections. Topics in these sections take up two views of the nature of cognitive musicology (Kugel, Laske), principles of modeling musical activity (Balaban, Bel, Blevis, Glasgow and Jenkins, Courtot, Smoliar), approaches to music composition (Ames and Domino, Laske, Marsella, Riecken), music analysis by synthesis (Cope, Ebcioglu, Maxwell), realtime performance of music (Bel and Kippen, Ohteru and Hashimoto), music perception (Desain and Honing, Jones, Miller and Scarborough, Linster), and learning/tutoring (Baker, Widmer).
M. Balaban is Senior Lecturer in the Department of Mathematics and Computer Science at Ben-Gurion University. K. Ebcioglu is Research Scientist in the Computer Sciences Department, IBM Thomas J. Watson Research Center. 0. Laske is a composer and President of NEWCOMP, Inc., The New England Computer Arts Association, Inc.
Knowledge Discovery in Databases brings together current research on the exciting problem of discovering useful and interesting knowledge in databases. It spans many different approaches to discovery, including inductive learning, bayesian statistics, semantic query optimization, knowledge acquisition for expert systems, information theory, and fuzzy 1 sets.
The rapid growth in the number and size of databases creates a need for tools and techniques for intelligent data understanding. Relationships and patterns in data may enable a manufacturer to discover the cause of a persistent disk failure or the reason for consumer complaints. But today's databases hide their secrets beneath a cover of overwhelming detail. The task of uncovering these secrets is called "discovery in databases." This loosely defined subfield of machine learning is concerned with discovery from large amounts of possible uncertain data. Its techniques range from statistics to the use of domain knowledge to control search.
Following an overview of knowledge discovery in databases, thirty technical chapters are grouped in seven parts which cover discovery of quantitative laws, discovery of qualitative laws, using knowledge in discovery, data summarization, domain?specific discovery methods, integrated and multi-paradigm systems, and methodology and application issues. An important thread running through the collection is reliance on domain knowledge, starting with general methods and progressing to specialized methods where domain knowledge is built in.
Topics include: Communication and Cooperation. Al and Education. User Interfaces. Natural Language. Distributed Al. Reasoning about Physical Systems. Perception, Planning, and Robotics. Machine Learning.
Books in the Innovative Applications of Artificial Intelligence (IAAI) series report on the nature and range of real-world problems that Al technology can address successfully today. The 22 applications described in this volume range from support for existing economic infrastructures such as monitoring foreign exchange transactions, assisting in recruiting industrial personnel, or screening news stories, to the creation of tomorrow's infrastructure elements such as software validation or planning for tunnel construction.
Partial Contents: CONSTRUE/TIS: A System for Content-Based Indexing of a Database of News Stories. ReValuator - An Expert System Approach to Actuarial Valuations. Inspector: An Expert System for Monitoring Worldwide Activities in Foreign Exchange. Computers Assist Humans in Human Resources. PREDICTE - An Intelligent System for Indicative Construction Time Estimation. Development of Expert Systems Supported Construction Planning for Shield Tunneling Method. Intelligent Text Comparison in Software Validation. Cooperating Artificial Neural and Knowledge-Based Systems in a Truck Fleet Brake-Balancing Application.
AI and Education. Automated Reasoning: automatic programming, planning and scheduling, rule-based reasoning, search, theorem proving, uncertainty, truth-maintenance systems, constraint-based systems. Cognitive Modeling. Commonsense Reasoning: qualitative reasoning, design, diagnosis, simulation. Impacts of AI Technology: organizational, economic, and social implications. Knowledge Acquisition and Expert System Design Methodologies: techniques for designing expert systems and acquiring domain knowledge. Knowledge Representation: knowledge-representation systems, inheritance, nonmonotonic logic, nonstandard logics, temporal reasoning. Machine Architectures and Computer Languages for AI. Machine Learning. Natural Language: generation and understanding; syntax, speech, dialogue. Perception and Signal Understanding: vision. Philosophical Foundations. Robotics. User Interfaces.