Showing papers in "Ai Communications in 1994"

Case-based reasoning: foundational issues, methodological variations, and system approaches

Abstract: Case-based reasoning is a recent approach to problem solving and learning that has got a lot of attention over the last few years. Originating in the US, the basic idea and underlying theories have spread to other continents, and we are now within a period of highly active research in case-based reasoning in Europe, as well. This paper gives an overview of the foundational issues related to case-based reasoning, describes some of the leading methodological approaches within the field, and exemplifies the current state through pointers to some systems. Initially, a general framework is defined, to which the subsequent descriptions and discussions will refer. The framework is influenced by recent methodologies for knowledge level descriptions of intelligent systems. The methods for case retrieval, reuse, solution testing, and learning are summarized, and their actual realization is discussed in the light of a few example systems that represent different CBR approaches. We also discuss the role of case-based methods as one type of reasoning and learning method within an integrated system architecture.

Toward a Practice of Autonomous Systems

Abstract: Toward a Practice of Autonomous Systems --Proc. of the First European Conference on Artificial Life, edited by F. Varela and P. Bourgine, The MIT Press, 1992, ISBN 0 262 72019 1, 515 pp.

Pattern Recognition by Self-Organizing Neural Networks

Abstract: Pattern Recognition by Self-Organizing Neural Networks edited by Gail A. Carpenter and Stephan Grossberg, MIT Press, 1991, ISBN 0-262-03176-0.

A survey on temporal reasoning in artificial intelligence

Abstract: The notion of time is ubiquitous in any activity that requires intelligence. In particular , several important notions like change, causality, action are described in terms of time. Therefore, the representation of time and reasoning about time is of crucial importance for many Artiicial Intelligence systems. Speciically during the last 10 years, it has been attracting the attention of many AI researchers. In this survey, the results of this work are analysed. Firstly, Temporal Reasoning is deened. Then, the most important repre-sentational issues which determine a Temporal Reasoning approach are introduced: the logical form on which the approach is based, the ontology (the units taken as primitives, the temporal relations, the algorithms that have been developed,.. .) and the concepts related with reasoning about action (the representation of change, causality, action,.. .). For each issue the diierent choices in the literature are discussed.

Temporal Reasoning in REAKT: An Environment for Real-Time Knowledge-Based Systems

Abstract: Temporal representation and reasoning, as the ability of reasoning about temporal data, representing past, current and expected application states, is an important function to be accomplished by Real-Time Knowledge-Based Systems RTKBS, since these systems are usually applied in dynamic time-dependent problem domains. However, this feature is not completely nor usually addressed in current RTKBS tools. In this paper, a RTKBS architecture is presented, with special emphasis on its temporal reasoning function, which is integrated in a RTKBS environment with a multi-agent blackboard architecture. Representation and management of temporal data, representing past, current and future problem states and reasoning processes within these contexts are detailed.

On-the-Fly Knowledge Base Refinement by a Classifier System

Abstract: A Classifier System CS is a machine learning system composed of a production system, a reinforcement learning mechanism, and a rule generation function by genetic algorithms GAs. This paper presents a new method for knowledge base refinement by CS technique and describes its application to rule-based simulation for an automated transportation system in a steel manufacturing process.The key idea of the proposed method is that the condition part of a rule should be divided into two parts: indispensable conditions and discriminate conditions. The former are generated by a diagnosing type knowledge-based system. The latter and action parts are generated and refined by genetic algorithms. Using this method, we can easily input initial rule sets, refine the rules without generating unapplicable ones, and reduce the computation time for learning. The method enables us to develop an on-the-fly knowledge refinement mechanism for rulebased simulation systems.Intensive experiments on the transportation system have shown that 1 the generated rules prevent blocking of indispensable events from occurring, and 2 the rules also generate useful sequences of events by means of the minimization of loss time of the shops in the process. The prerequisites of the proposed method are so general that the method can be widely applied to the rule refinement tasks in various kinds of rule-based systems.

Computing and Information Compression: A Reply

Abstract: An earlier article [25] discusses the proposition that the storage and processing of information in computers and in brains may often be understood as information compression. A subsequent article [15] criticises the computing aspects of [25] and research on the more specific conjecture that all forms of computing and formal reasoning may usefully be understood as information compression.The present article, which is intended to be intelligible without recourse to earlier articles, answers the main points in [15], tries to correct the many inaccuracies and misconceptions in that article, and discusses related issues.Topics which are discussed include: the way theories are or should be developed; the role of evidence in motivating research; apparent shortcomings in the Turing machine concept as a reason for seeking new principles of computing; the apparent conflict between the idea of 'computing as compression' and the fact that computers may create redundancy-and how the contradiction may be resolved; monotonicity and non-monotonicity of functions; information theory as a basis for 'computing as compression'; computer models of a proposed 'new generation' computing system dedicated to information compression by pattern matching, unification and metrics-guided search and how, within this framework, the effect of re-write rules may be imitated; how information may be transposed from one place to another; and how the effect of procedural programming may be achieved; computational complexity of information compression; the relationship of current proposals to research on inductive inference and algorithmic information theory.

Knowledge-Base Evolution for Product and Production Planning

Abstract: Knowledge-base evolution techniques are shown to be of critical importance for the successful application of knowledge-based systems in complex domains. By conceptualizing knowledge-base evolution as theory revision, we can take advantage of the basic findings from different research communities. Results from Inductive Logic Programming ILP and Explanation-Based Learning EBL provide a set of techniques that can be used as a foundation for obtaining new knowledge knowledge-base exploration. Techniques from deductive database research might be used for testing the correctness of a knowledge base knowledge base verification. By an interactive application of these exploration and verification techniques, domain experts and other users may similarly improve the effectiveness of the knowledge base knowledge validation. The application of such selected techniques is then discussed with respect to the specific problem of improving production parameters.

Artificial Intelligence through Logic

Abstract: The arguments for and against the use of logic in artificial intelligence are discussed, including the argument on the declarative versus procedural view of knowledge. The author sees that both arguments regarding the suitability or unsuitability of logic for AI have their merits. A position that integrates both arguments is presented which includes the paradigm of logic programming. Beyond symbolic AI, we have also incorporated connectionism in the integration.

PCLEARN: A Computer Model for Learning Perceptual Chunks

Abstract: Acquiring search control knowledge of high utility is essential to reasoners in speeding up their problem-solving performance. In the domain of geometry problem-solving, the role of “perceptual chunks”, an assembly of diagram elements many problems share in common, in effectively guiding problem-solving search has been extensively studied, but the issue of learning these chunks from experiences has not been addressed so far. Although the explanation-based learning technique is a typical learner for search control knowledge, the goal-orientedness of its chunking criterion leads to produce such search control knowledge that can only be used for directly accomplishing a target-concept, which is totally different from what perceptual-chunks are for. This paper addresses the issues of acquiring domain-specific perceptual-chunks and demonstrating the utility of acquired chunks. The proposed technique is that the learner acquires, for each control decision node in the problem-solving traces, a chunk which is an assembly of diagram elements that can be visually recognizable and grouped together with the control decision node. Recognition rules implement this chunking criterion in the learning system PCLEARN. We show the feasibility of the proposed technique by investigating the cost-effective utility of the learned perceptual chunks in the geometry domain, and also discuss the potential for the technique being applied to other domains.

Software Secretary Kernel: An Extendable Architecture for Learning and Negotiating Personal Assistants

Abstract: Software secretaries are agents that provide assistance in managing some office-work scheduling meetings, reserving rooms, processing purchase orders in much the same way as human secretaries. This concept seems attractive, since it could provide secretarial assistance to everyone within an organization that is presently available to only few people. To maximize their usefulness, software secretaries have to be customized to users' and organizations' needs, they must be extendable for supporting new tasks, and they need capabilities to negotiate with humans and agents on behalf of their owners. The proposed software secretary kernel is the architecture for implementing such flexible personal assistance programs.

Computing and Information Compression

Abstract: An earlier article [25] discusses the proposition that the storage and processing of information in computers and in brains may often be understood as information compression. A subsequent article ...

Report on the 1993 Bolzano International School in Philosophy and Artificial Intelligence: NLP and Multilingualism

Abstract: We will present the important topics dealt with by the lecturers, relate them to each other, we will expand on the aspects of these topics that relate to linguistics and artificial intelligence and eventually relate them to past or ongoing work at the VUB Artificial Intelligence Laboratory. We are particularly interested in the interaction between artificial intelligence and natural language processing: to what extent are similar problems encountered and how are they tackled in each field?