If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."
However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …
The central thesis of my dissertation (Kocabas 1989)1 is that in complex systems, descriptive and definitive knowledge can be organized into functional categories; this categorization provides clarity and efficiency in representation and facilitates the integrated use of various methods of learning. I describe a formalism for organizing knowledge into such functional categories and some of its implementations. In this formalism, descriptive scientific knowledge is classified into seven categories. The categorization formalism allows complex propositions to be analyzed into their simple constituents; in turn, these constituents can be maintained in their categories. They can then be combined using a simple transformation function to form complex constructs such as frames and schemata. The methodology facilitates the implementation of knowledge-level methods of learning such as similarity-based learning, explanation-based learning, and conceptual clustering. It simplifies the identification and resolution of conflicts in knowledge systems.
The workshop "Advances in Interfacing Production Systems with the Real World" was designed to bring together researchers from around the world to focus on the problem of integrating production systems into industrial environments. It was held on 25 August 1991 in Sydney, Australia, in conjunction with the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91). Nine papers were accepted for the proceedings, and six of them were discussed at the workshop.
An engineer who creates a design needs to determine whether the design is free of errors that can lead to high manufacturing costs, tragic accidents because of design defects, low use because of poor product quality, and a host of other downstream concerns. The domain of engineering design is much harder than other domains, and errors are more likely to arise and remain undetected until it is too late to do something about them. One way to reduce these errors is to introduce the use of expert critics into the designer's electronic support environment. Critics are a promising approach for organizing a next-generation design support environment (DSE). Unfortunately, expert-critiquing theory offers inaccurate but widely followed guidance for helping builders create usable critic programs. Existing critics rely on batch, after-task, debiasing of experts. This form of criticism turns out to be overly limited and too often leads to user frustration. As a step toward correcting this deficiency, this article presents lessons learned from following the incorrect theory along with guidance for a more robust approach to criticism system construction. Future research needs are also identified that should help builders realize the full potential of critics in engineering DSEs.
. It is argued that Situated Agents should be designed using a unitaryon-line computational model. The Constraint Net model of Zhang and Mackworth satisﬁesthat requirement. Two systems for situated perception built in our laboratory are describedto illustrate the new approach: one for visual monitoring of a robot’s arm, the other forreal-time visual control of multiple robots competing and cooperating in a dynamic world.First proposal for robot soccer.Proc. VI-92, 1992. later published in a book Computer Vision: System, Theory, and Applications, pages 1-13, World Scientific Press, Singapore, 1993.