A framework for skill acquisition is proposed that includes two major stages in the development of a cognitive skill: a declarative stage in which facts about the skill domain are interpreted and a procedural stage in which the domain knowledge is directly embodied in procedures for performing the skill. This general framework has been instantiated in the ACT system in which facts are encoded in a propositional network and procedures are encoded as productions. Knowledge compilation is the process by which the skill transits from the declarative stage to the procedural stage. It consists of the subprocesses of composition, which collapses sequences of productions into single productions, and proceduralization, which embeds factual knowledge into productions. Once proceduralized, further learning processes operate on the skill to make the productions more selective in their range of applications. These processes include generalization, discrimination, and strengthening of productions. Comparisons are made to similar concepts from past learning theories. How these learning mechanisms apply to produce the power law speedup in processing time with practice is discussed. It requires at least 100 hours of learning and practice to acquire any significant cognitive skill to a reasonable degree of proficiency. For instance, after 100 hours a student learning to program a computer has achieved only a very modest facility in the skill. Learning one's primary language takes tens of thousands of hours. The psychology of human learning has been very thin in ideas about what happens to skills under the impact of this amount of learning—and for obvious reasons. This article presents a theory about the changes in the nature of a skill over such large time scales and about the basic learning processes that are responsible.

A formalism is presented for computing and organizing actions for autonomous agents in dynamic environments. We introduce the notion of teleo-reactive (T-R) programs whose execution entails the construction of circuitry for the continuous computation of the parameters and conditions on which agent action is based. In addition to continuous feedback, T-R programs support parameter binding and recursion. A primary di erence between T-R programs and many other circuit-based systems is that the circuitry of T-R programs is more compact; it is constructed at run time and thus does not have toanticipate all the contingencies that might arise over all possible runs. In addition, T-R programs are intuitive and easy to write and are written in a form that is compatible with automatic planning and learning methods. We brie y describe some experimental applications of T-R programs in the control of simulated and actual mobile robots. 1.

Explanations for decisions made by a policy framework allow end users to understand how the results were obtained, increase trust in the policy decision and enforcement process, and enable policy administrators to ensure the correctness of the policy. In our framework, an explanation for any statement including a policy decision is a representation of the list of reasons (known as dependencies) associated with its derivation. Dependency tracking involves maintaining the list of reasons (statements and rules) for the derivation of a new statement. In this paper, we describe our policy approach that (i) provides explanations for policy decisions, (ii) provides more efficient and expressive reasoning through the use of nested sub-rules and goal direction, and (iii) is grounded in Semantic Web technologies. We discuss the characteristics of our approach and provide a brief overview of the AIR policy language that implements it. We also discuss how relevant explanation information is identified and presented to end users and describe our preliminary graphical user interface. 1

Expertise in fault diagnosis often depends on recognizing particular patterns in observed data corresponding to situations that have previously been 6een and correctly interpreted This approach can result in significant efficiencies by avoiding a costly and detailed analysis based on the causal relationships between faults and observable data Recognition-based reasoning requires highly focused search strategies in order to extract relevant information from a knowledge base that contains a large number of prototypes for various possible faults This paper describes a model of recognition-based reasoning and describes an implementation of the model. designed to solve diagnostic problems in pediatric cardiology The model first

What is the match cost of adding a new rule to a production system (rule-based system)? Two conflicting views have emerged. Research in EBL indicates that learned rules add to the match cost of a production system. Thus, as the production system size increases with learning, the match cost will also increase. There is much data in the literature to support this phenomenon. On the contrary, researchers in parallel production systems have concluded that the match effort in a production system is limited, independent of the size of the production system. Thus, an increase in the size of the production system will not lead to an increase in the match cost. There is much data to support this phenomenon as well. In this paper, we point out these contradictory views of production match in the two research communities. A direct analysis of these conflicting views is difficult, since the two communities have worked with vastly different systems. Therefore, we have developed some large production systems in Soar, to analyze the situation within a common framework. This common framework narrows down the possible causes for this conflict, and raises important questions for future work.

In this paper, we study how several aspects of the Conceptual Graph theory can be implemented using the pattern-matching mechanisms of production systems. Usually, standard pattern matching applies to arbitrary data that, unlike CGs, do not rely on a particular theory. Reconstructions of Conceptual Graphs in terms of basic graphs have been proposed in the literature. We show that K, a graph representation language with "high-level" (rule-based) graph manipulation facilities, allows an elegant implementation of these proposals. We show how the CG projection is reconstructed from standard pattern matching. Such a mechanism provides the user with graph retrieval facilities. Moreover, K's inherent features, such as forward reasoning rules, are gracefully transferred to the resulting CG implementation with no further effort. The result is a production system that operates within the CG theory thus providing the basis for a flexible CG processor. Jacques Bouaud and Pierre Zweig...

This paper describes a rule-based machine learning approach to morphological processing in the system called XMAS. XMAS discovers and quires hngtistic rules from examples of morphological combinations and accomphshes the morphological analysis and synthesis by applying the rules. This approach is independent of languages, saves time and effort for development and maintenance, and takes small lexicon space. A Korean version of XMAS is effectively working in the English-Korean machine translation system KSHALT.

The knowledge organization of a rule-based damage assessment system of existing structures subjected to earthquake excitation is outlined in this paper. A principle of inexact inference to obtain a rational solution is presented. The fuzzy set theory and the production system with certainty factor are employed jointly in the inexact inference to deal with the continuous nature of the damage state and to attain the modularity of uncertain knowledge, respectively. The role of damage assessment of existing structures has received increasing attention recently [32,33,343. Existing structures refer to

Recent advances in programming languages study and design have established a standard way of grounding computational systems representation in category theory. These formal results led to a better understanding of issues of control and side-e#ects in functional and imperative languages.

I hereby declare that I am the sole author of this thesis. This is a true copy of the thesis, including any required final revisions, as accepted by my examiners. I understand that my thesis may be made electronically available to the public. ii An automatically trained, statistically based, fuzzy inference system that functions as a classifier is produced. The hybrid system is designed specifically to be used as a decision support system. This hybrid system has several features which are of direct and immediate utility in the field of decision support, in-cluding a mechanism for the discovery of domain knowledge in the form of explanatory rules through the examination of training data; the evaluation of such rules using a simple probabilistic weighting mech-anism; the incorporation of input uncertainty using the vagueness abstraction of fuzzy systems; and the provision of a strong confidence measure to predict the probability of system failure. Analysis of the hybrid fuzzy system and its constituent parts allows commentary on the weighting scheme and performance of the “Pattern Discovery ” system on which it is based. Comparisons against other well known classifiers provide a benchmark of the performance of the