scispace - formally typeset
Search or ask a question

Showing papers on "Applications of artificial intelligence published in 1993"


Journal ArticleDOI
TL;DR: Adaptive autonomous agents as mentioned in this paper are systems that inhabit a dynamic, unpredictable environment in which they adapt to the environment in a way similar to humans. But adaptive autonomous agents are not always suitable for humans.
Abstract: One category of research in Artificial Life is concerned with modeling and building so-called adaptive autonomous agents, which are systems that inhabit a dynamic, unpredictable environment in whic...

555 citations


Journal ArticleDOI
TL;DR: The paper addresses this Artificial Life route toward AI and reviews some of the results obtained so far.
Abstract: Behavior-oriented Artificial Intelligence (AI) is a scientific discipline that studies how behavior of agents emerges and becomes intelligent and adaptive. Success of the field is defined in terms of success in building physical agents that are capable of maximizing their own self-preservation in interaction with a dynamically changing environment. The paper addresses this Artificial Life route toward AI and reviews some of the results obtained so far.

235 citations


Book
01 Apr 1993
TL;DR: Based on the author's course at Stanford University, Essentials of Artificial Intelligence is an integrated, cohesive introduction to the field that combines clear presentations with humor and AI anecdotes.
Abstract: Since its publication, Essentials of Artificial Intelligence has been adopted at numerous universities and colleges offering introductory AI courses at the graduate and undergraduate levels. Based on the author's course at Stanford University, the book is an integrated, cohesive introduction to the field. The author has a fresh, entertaining writing style that combines clear presentations with humor and AI anecdotes. At the same time, as an active AI researcher, he presents the material authoritatively and with insight that reflects a contemporary, first hand understanding of the field. Pedagogically designed, this book offers a range of exercises and examples. Table of Contents 1 Introduction: What is AI? 2 Overview 3 Blind Search 4 Heuristic Search 5 Adversary Search 6 Introduction to Knowledge Representation 7 Predicate Logic 8 First-Order Logic 9 Putting Logic to Work: Control of Reasoning 10 Assumption-Based Truth Maintenance 11 Nonmonotonic Reasoning 12 Probability 13 Putting Knowledge to Work: Frames and Semantic Nets 14 Planning 15 Learning 16 Vision 17 Nature Language 18 Expert Systems 19 Concluding Remarks

196 citations


Book
01 Jan 1993
TL;DR: This book provides an introduction to artificial intelligence methods, written specifically for science students, and should be of interest to any college-level student who wants to know more about how computers can help to understand and interpret science.
Abstract: From the Publisher: This series of short texts provides accessible accounts of a range of essential topics in chemistry. Written with the needs of the student in mind, the Oxford Chemistry Primers offer just the right level of detail for undergraduate study, and will be invaluable as a source of material commonly presented in lecture courses yet not adequately covered in existing texts. All the basic principles and facts in a particular area are presented in a clear and straightforward style, to produce concise yet comprehensive accounts of topics covered in both core and specialist courses. It is becoming evident that the techniques of artificial intelligence are useful for more than just the development of thinking machines; they constitute powerful problem-solving tools in their own right. The large-scale, complex problems most suited to AI are just those which are most difficult for conventional techniques to solve. AI methods therefore expand the range of problems in science that we can successfully tackle. Because of a recent rapid growth in computing power, these methods can now be used on a routine basis by scientists in both academic research and the commercial world. It is becoming vital that science students be exposed to and understand these techniques. This book provides an introduction to these methods, written specifically for science students. Although examples are drawn mainly from chemistry, the book is suitable for a more general audience, and should be of interest to any college-level student who wants to know more about how computers can help us to understand and interpret science.

131 citations


Journal ArticleDOI
TL;DR: This article proposes real-world software environments, such as operating systems or databases, as a complementary substrate for intelligent-agent research and considers the relative advantages of software environments as test beds for AI.
Abstract: In his recent papers, entitled Intelligence without Representation and Intelligence without Reason, Brooks argues for mobile robots as the foundation of AI research. This article argues that even if we seek to investigate complete agents in real-world environments, robotics is neither necessary nor sufficient as a basis for AI research. The article proposes real-world software environments, such as operating systems or databases, as a complementary substrate for intelligent-agent research and considers the relative advantages of software environments as test beds for AI. First, the cost, effort, and expertise necessary to develop and systematically experiment with software artifacts are relatively low. Second, software environments circumvent many thorny but peripheral research issues that are inescapable in physical environments. Brooks's mobile robots tug AI toward a bottom-up focus in which the mechanics of perception and mobility mingle inextricably with or even supersede core AI research. In contrast, the softbots (software robots) I advocate facilitate the study of classical AI problems in real-world (albeit, software) domains. For example, the UNIX softbot under development at the University of Washington has led us to investigate planning with incomplete information, interleaving planning and execution, and a host of related high-level issues.

75 citations


Proceedings Article
28 Aug 1993
TL;DR: This Computers and Thought Award lecture will argue that massively parallel artificial intelligence will add new dimensions to the ways that the AI goals are pursued, and demonstrate that massively Parallel artificial intelligence is where AI meets the real world.
Abstract: Artificial Intelligence has been the field of study for exploring the principles underlying thought, and utilizing their discovery to develop useful computers. Traditional AI models have been, consciously or subconsciously, optimized for available computing resources which has led AI in certain directions. The emergence of massively parallel computers liberates the way intelligence may be modeled. Although the AI community has yet to make a quantum leap, there are attempts to make use of the opportunities offered by massively parallel computers, such as memory-based reasoning, genetic algorithms, and other novel models. Even within the traditional AI approach, researchers have begun to realize that the needs for high performance computing and very large knowledge bases to develop intelligent systems requires massively parallel AI techniques. In this Computers and Thought Award lecture, I will argue that massively parallel artificial intelligence will add new dimensions to the ways that the AI goals are pursued, and demonstrate that massively parallel artificial intelligence is where AI meets the real world.

55 citations


Journal ArticleDOI
TL;DR: In the early 1970s, a bolder and more applied inclination to choose complex real-world problems as task environments became evident as mentioned in this paper, which was both successful and exciting, in two ways: first, the AI programs were achieving high levels of competence at solving certain problems that human specialists found challenging.

51 citations



Book
Yoav Shoham1
01 Jan 1993
TL;DR: This unique book is a broad, clear presentation of artificial intelligence (AI) problem-solving techniques that selects the most important among the well-defined algorithms and procedures in the field, explains them in plain language, and, where appropriate, provides ALGOL-like descriptions of them.
Abstract: From the Publisher: This unique book is a broad, clear presentation of artificial intelligence (AI) problem-solving techniques. It selects the most important among the well-defined algorithms and procedures in the field, explains them in plain language, and, where appropriate, provides ALGOL-like descriptions of them. Every technique is implemented in Prolog, a language that is quickly learned and allows for easy experimentation in a learning environment. The book includes complete source listings, and the software is available online. This book is ideal for hands-on courses in Al programming. It is also a useful primary or supplementary text in general introductory AI courses and a complete sourcebook for the practitioner.

41 citations


Journal ArticleDOI
TL;DR: The 1978 paper reviewed the artificial intelligence-based medical (AIM) diagnostic systems and identified the underlying knowledge on which each operated and classified the general methods they used.

33 citations


Journal ArticleDOI
TL;DR: The author studied the Japanese involvement in the field of artificial intelligence (AI) and visited eight Japanese RD problems in AI applications development and their solutions; practical system examples; and AI applications to power systems of the future.
Abstract: The author studied the Japanese involvement in the field of artificial intelligence (AI) and visited eight Japanese RD problems in AI applications development and their solutions; practical system examples; and AI applications to power systems of the future. Out of the 97 papers cited, ten were produced by electric utilities, ten by manufacturers, 17 by universities, and 60 were joint efforts. This shows the level and importance of joint collaborative research among the Japanese researchers. Even though they are working on many theoretical aspects of the AI technology, including automated knowledge acquisition and verification, they still use a significant amount of theoretical work done in the US for successful prototyping of AI based tools. The use of AI tools in the Japanese electric power industry is far more widespread than what is seen in the US or in Europe. >

01 Jan 1993
TL;DR: A functional description of an integrated construction project document management system (ICPDM) system which focuses on the management of the different documents produced by the different participants in the construction process.
Abstract: The emphasis in research concerning methods for computer integrated construction has recently been on advanced data base techniques (product models) and AI applications. Another type of computer-aid for integration which could have a significant impact on practice in a shorter time-frame focuses on the management of the different documents which are produced by the different participants in the construction process. A functional description of such an integrated construction project document management (ICPDM) system is presented in the paper.

Proceedings Article
07 Dec 1993
TL;DR: The multi-layer feedforward network is introduced and the problems in establishing neural network approaches based on this network for power system applications are discussed.
Abstract: This paper reviews the applications of artificial intelligence and neural networks in power engineering. It first reports areas in power systems that artificial intelligence has been applied to. It then summarises the artificial intelligence techniques which have been employed and makes suggestions for the improvement of existing artificial intelligence tools. Following this, the paper concentrates on neural networks and their applications to power systems. The multi-layer feedforward network is introduced and the problems in establishing neural network approaches based on this network for power system applications are discussed. Future themes for further development in artificial intelligence and neural network applications in power systems are proposed. >

Book
01 Oct 1993
TL;DR: Knowledge acquisition and knowledge representation inference techniques and architectures man-machine interfaces reasoning with uncertainty and imprecision machine learning neutral networks and parallel models of intelligence software engineering of AI systems strategic impact on organizations the AI market is studied.
Abstract: Knowledge acquisition and knowledge representation inference techniques and architectures man-machine interfaces reasoning with uncertainty and imprecision machine learning neutral networks and parallel models of intelligence software engineering of AI systems strategic impact on organizations the AI market.

Journal ArticleDOI
TL;DR: The class of multi-join queries have received much attention because join is the most expensive relational operation and many applications require access to multiple relations, so any performance improvement that can be made in processing multijoin queries will be beneficial.

Journal ArticleDOI
TL;DR: An analysis of both neural networks and expert systems applications in terms of their capabilities and weaknesses is presented, using examples of financial applications of expert systems and neural networks to provide a unified context.
Abstract: Neural networks and expert systems are two major branches of artificial intelligence (AI). Their emergence has created the potential for a new generation of computer‐based applications in the area of financial decision making. Both systems are used by financial institutions and corporations for a variety of new applications from credit scoring to bond rating to detection of credit card fraud. While both systems belong to the applied field of artificial intelligence, there are many differences between them which differentiate their potential capabilities in the field of business. Presents an analysis of both neural networks and expert systems applications in terms of their capabilities and weaknesses. Uses examples of financial applications of expert systems and neural networks to provide a unified context for the comparison.

Proceedings ArticleDOI
03 Nov 1993
TL;DR: A "hormone mechanism", which is part of the behavior definition language, was used to generate artificial emotion and the action selection dynamics (ASD) paradigm proposed by Pattie Maes as a way to implement computational reflection was tried.
Abstract: Although some researchers claim that emotion is unique to mammals, this paper describes a notion of artificial emotion as a phenomenon resulting from a series of modifications to emergent behaviors generated by a behavior-based artificial intelligence (AI) approach. Such modifications to behaviors are caused by stimuli (including those from humans) which a robot receives from its environment. The paper describes a series of experiments to generate and test artificial emotion using subsumption architecture (SA) robot platforms developed by the Massachusetts Institute of Technology (MIT). A "hormone mechanism", which is part of the behavior definition language, was used to generate artificial emotion. In addition, the action selection dynamics (ASD) paradigm proposed by Pattie Maes as a way to implement computational reflection was also tried. The latter is expected to permit the authors to investigate more profound ontological issues associated with artificial emotion as part of the experiments in computational reflection. >

Journal ArticleDOI
TL;DR: The field of AI is directed at the fundamental problem of how the mind works; its approach, among other things, is to try to simulate its working -- in bits and pieces.
Abstract: The field of AI is directed at the fundamental problem of how the mind works; its approach, among other things, is to try to simulate its working -- in bits and pieces. History shows us that mankind has been trying to do this for certainly hundreds of years, but the blooming of current computer technology has sparked an explosion in the research we can now do. The center of AI is the wonderful capacity we call learning, which the field is paying increasing attention to. Learning is difficult and easy, complicated and simple, and most research doesn't look at many aspects of its complexity. However, we in the AI field are starting. Let us now celebrate the efforts of our forebears and rejoice in our own efforts, so that our successors can thrive in their research. This article is the substance, edited and adapted, of the keynote address given at the 1992 annual meeting of the Association for the Advancement of Artificial Intelligence on 14 July in San Jose, California.

Book ChapterDOI
William A. Gale1
TL;DR: Artificial Intelligence (AI) has now provided some effective techniques for formalization of knowledge about goals and actions that could open new areas of research to statisticians.
Abstract: Artificial Intelligence (AI) has now provided some effective techniques for formalization of knowledge about goals and actions. These techniques could open new areas of research to statisticians. Experimental systems designed to assist users of statistics have been constructed in experiment design, data analysis technique application, and technique selection. Knowledge formalization has also been used in experimental programs to assist statisticians in doing data analysis and in building consultation systems.


Proceedings ArticleDOI
29 Nov 1993
TL;DR: The document highlights the necessity for AI in telecommunications and provides a survey of AI techniques and describes work being carried out in this field at Strathclyde University.
Abstract: As society is propelled towards the information age, the key component of this change, the telecommunications network faces rapid and profound transformations. Novel approaches such as artificial intelligence (AI) will be essential to achieve these transformations efficiently. The paper is aimed at those engineers who, although familiar with telecommunications, may be unsure of artificial intelligence techniques. The document highlights the necessity for AI in telecommunications and provides a survey of AI techniques. Finally, it describes work being carried out in this field at Strathclyde University. >

Proceedings ArticleDOI
25 Apr 1993
TL;DR: The authors suggest that uncertainty may be managed naturally, and even used profitably, in cooperative, self-organizing, dynamical physical systems, and in neural networks.
Abstract: Uncertainty in AI applications, as they apply to inductive inference, is often dealt with by modeling heuristic methods of inference based on different kinds of logic, binary, multivalued or fuzzy, simulated on digital computers with probability, possibility or belief theories. The authors suggest that uncertainty may be managed naturally, and even used profitably, in cooperative, self-organizing, dynamical physical systems, and in neural networks. New classes of powerful cooperative computation and learning (C&L) machines are possible, with the class of artificial neural networks being just an early, rather rudimentary, example. The temporal behavior of classical dynamical physical systems was investigated for C&L models. The case of deterministic chaos is considered in studying C&L properties in dynamical system behavior. Deterministic chaos underlines the behavior of a class of physical systems of special interest, whose unpredictability is derived from sensitive dependence on initial conditions in a sustained way which exaggerates uncertainty. Non-Lipschitzian unpredictability is considered. >

Journal ArticleDOI
TL;DR: More research is needed before a general statistical expert system is successful and expert systems which are more specialized may be more feasible, according to Hahn.
Abstract: Introduction Artificial Intelligence has been applied to a variety of areas in the fields of statistics and process control. Expert systems have ranged from statistical "consultants" to robotic vision systems. Hand outlined the development of a statistical "consultant" based on studying the way a consultant approached a problem and addressed problems that could be encountered in the development of the system[1]. Hahn defined a "statistical expert system" as an automated statistical consultant and data analyst that guides the analyst directly to a solution of a general statistical problem[2]. But, Hahn concluded, more research is needed before a general statistical expert system is successful and expert systems which are more specialized may be more feasible. There are specialized systems in quality and process control which exist in the manufacturing area. Giovannone discussed the integration of robots in several locations around Italy[3]. These robots take measurements but most of them only have an interface to a program that controls the sampling and records the information. Haton also describes the application of artificial intelligence to sample inspection[4]. The integration of vision systems used for quality inspection will expand during the next decade, according to Haton. An expert system to monitor the vision system is a possibility. Ackerman, Plsek and Surette describe some systems developed by AT&T for internal corporate use[5]. Most systems mentioned by them operate in real time and cover aspects of process control such as product yields, reliability analysis and quality cost planning. A few commercial packages implementing artificial intelligence are available for quality control. A survey of packages a few years ago indicated that a few packages by A. William Wortham and Associates analyse charts using artificial intelligence[6]. The analyses in these packages consisted of "several statistical tests, all combined through artificial intelligence to give a considered decision". There are many more software packages that perform chart analysis but do not mention artificial intelligence applications. Most of the packages only test for a small number of patterns, like shifts and trends, or use runs rules for detection. There is no mention of accuracy of these packages or the false alarm rate for the tests performed.

Book ChapterDOI
01 Jan 1993
TL;DR: There exists a spectrum of applications software that ranges from the traditional data processing systems to advanced artificial intelligence applications, and there is expanding interest in artificial intelligence.
Abstract: There exists a spectrum of applications software that ranges from the traditional data processing systems to advanced artificial intelligence applications (see Fig. 19.1). The sophistication and complexity of these applications softwares is steadily increasing. While conventional systems, such as data processing and management information systems, still exist and are quite appropriate for some manufacturing applications, there is expanding interest in artificial intelligence (Savino, 1990).


01 Oct 1993
TL;DR: Since artificial intelligence techniques became aligned with conventional computer hardware architectures in the middle 1980s, economical applications to E P needs have become available and all four have evolved such that practical applications have been produced.
Abstract: Since artificial intelligence (AI) techniques became aligned with conventional computer hardware architectures in the middle 1980s, economical applications to E P needs have become available. Expert systems, fuzzy logic systems, neural networks and genetic algorithms are four AI technologies having a major impact in the petroleum industry. At present, these technologies are at different stages of maturity. Expert systems are the most mature, and genetic algorithms the least. However, all four have evolved such that practical applications have been produced. Further progress in applying AI to the petroleum industry will come through combining two or more of these techniques. In addition, other AI techniques such as case-based reasoning and database mining continue to be introduced. An introduction to these techniques and a look at their current practical applications is presented.

01 Jan 1993
TL;DR: In this paper, a case-based reason-based approach is used for adaptive architectures in the context of computer aided manufacturing (CAM) and Fuzzy Logic and Control (FLC).
Abstract: Abstract : CONTENTS: Adaptive architectures; Case-based reasonong; Computer aided manufacturing; Diagnosis; Fuzzy logic and control; Image; Knowledge acquisition; Knowledge based systems; Model based- reasoning; Modelling; Software engineering; Invited presentation. (KAR) p. 3

Proceedings ArticleDOI
12 Oct 1993
TL;DR: A set of algorithms which uses Subsumption Architecture for controlling vehicles operating in close vicinity has been developed and a successful application of the approach to a small-scale but fully situated and embodied vehicle control problem using scaled down mobile robots is described.
Abstract: In behavior-based artificial intelligence (AI), intelligence is realized as an emergent process which arises from interactions between otherwise "unintelligent" simple behaviors of agents and between these agents and their environment. A set of algorithms which uses Subsumption Architecture (SA) for controlling vehicles operating in close vicinity has been developed. SA is a dominant behavior-based AI technique. The algorithms collectively generate desirable manoeuver capabilities for vehicles which must travel through a dynamic interactive environment. A successful application of the approach to a small-scale but fully situated and embodied vehicle control problem using scaled down mobile robots is described.