The problem of formulating general concepts from specific training examples has long been a major focus of machine learning research. While most previous research has focused on empirical methods for generalizing from a large number of training examples using no domain-specific knowledge, in the past few years new methods have been developed for applying domain-specific knowledge to formulate valid generalizations from single training examples. The characteristic common to these methods is that their ability to generalize from a single example follows from their ability to explain why the training example is a member of the concept being learned. This paper proposes a general, domain-independent mechanism, called EBG, that unifies previous approaches to explanation-based generalization. The EBG method is illustrated in the context of several example problems, and used to contrast several existing systems for explanation-based generalization. The perspective on explanation-based generalization afforded by this general method is also used to identify open research problems in this area.

/pdf/explanation-based-generalization-a-unifying-view-kfrrptjv86.pdf

Explanation-based generalization: a unifying view

/pdf/editorial-on-machine-learning-362proz98p.pdf

Editorial: On Machine Learning

Diagnostic reasoning based on structure and behavior

Most artificial intelligence research investigates intelligent behavior for a single agent--solving problems heuristically, understanding natural language, and so on. Distributed Artificial Intelligence (DAI) is concerned with coordinated intelligent behavior: intelligent agents coordinating their knowledge, skills, and plans to act or solve problems, working toward a single goal, or toward separate, individual goals that interact. DAI provides intellectual insights about organization, interaction, and problem solving among intelligent agents. This comprehensive collection of articles shows the breadth and depth of DAI research. The selected information is relevant to emerging DAI technologies as well as to practical problems in artificial intelligence, distributed computing systems, and human-computer interaction. 

"Readings in Distributed Artificial Intelligence" proposes a framework for understanding the problems and possibilities of DAI. It divides the study into three realms: the natural systems approach (emulating strategies and representations people use to coordinate their activities), the engineering/science perspective (building automated, coordinated problem solvers for specific applications), and a third, hybrid approach that is useful in analyzing and developing mixed collections of machines and human agents working together. 

The editors introduce the volume with an important survey of the motivations, research, and results of work in DAI. This historical and conceptual overview combines with chapter introductions to guide the reader through this fascinating field. A unique and extensive bibliography is also provided.

Readings in Distributed Artificial Intelligence

In the last issue of this journal Mitchell, Keller, and Kedar-Cabelli presented a unifying framework for the explanation-based approach to machine learning. While it works well for a number of systems, the framework does not adequately capture certain aspects of the systems under development by the explanation-based learning group at Illinois. The primary inadequacies arise in the treatment of concept operationality, organization of knowledge into schemata, and learning from observation. This paper outlines six specific problems with the previously proposed framework and presents an alternative generalization method to perform explanation-based learning of new concepts.

/pdf/explanation-based-learning-an-alternative-view-3wnor0sw84.pdf

Explanation-Based Learning: An Alternative View

It is by now well-recognised that a major impediment to developing know ledge-based systems is the knowledge acquisition bottleneck the task of building up a complete enough and correct enough knowledge base to provide high-level performance. This paper proposes a new class of knowledge-based systems designed to address this knowledge-acquisition bottleneck by incorporating a learning component to acquire new knowledge through experience. In particular, we define Learning Apprentice Systems as the class of interactive knowledge-based consultants that directly assimilate new knowledge by observing and analyzing the problem solving steps contributed by their users through their normal use of the system. This paper describes a specific Learning Apprentice System, called LEAP, which is presently being developed in the domain of VLSI design We also discuss design issues for Learning Apprentice Systems more generally, as well as restrictions on the generality of our current approach.

/pdf/leap-a-learning-apprentice-for-vlsi-design-ucd3yn4eh6.pdf

LEAP: a learning apprentice for VLSI design

A framework is presented for constructing knowledge-based aids for design problems. In particular, we describe the organization of an interactive knowledge-based consultant for VLSI design (called VEXED?an acronym for VLSI expert editor), and a prototype implementation of VEXED. The paper focuses on the principles underlying the design of VEXED, and on several lessons and research issues that have arisen from implementing and experimenting with this prototype.

A Knowledge-Based Approach to Design

Underlying any system that does design is a model of the design process and a division oflabor between the system and the user We are just beginning to understand what the main alternative models are, what their strengths and weaknesses are, and for which domains and tasks each is appropriate The research reported here is an attempt to further that understanding by studying a particular model, the model of design as top down refinement plus constraint propagation, with the user making control decisions and the system carrying them out We have studied this model by embodying it in VEXED, a design aid for NMOS digital circuits, and by experimenting with this system Our primary conclusion is that this model needs further elaboration, but seems like a good basic model on which to build such systems

Design as refinement plus constraint propagation: the VEXED experience

Digital circuit redesign is a task that requires knowledge of circuit structure, function, and purpose, and of the interrelationships among these. We describe a knowledge-based system, REDESIGN, which assists in the redesign of digital circuits to meet altered functional specifications. REDESIGN assists the user in focusing on an appropriate portion of the circuit, generating possible local changes within the circuit, ranking these possible changes, and detecting undesirable side-effects of redesigns. It provides this assistance by combining two modes of reasoning about circuits: (1) causal reasoning involving analysis of circuit operation, and (2) reasoning about the purposes, or roles, of various circuit modules within the larger circuit. We describe these two modes of reasoning, and the way in which they are combined by REDESIGN to provide aid in circuit redesign.

/pdf/an-intelligent-aid-for-circuit-redesign-23blzzu5qw.pdf

An intelligent aid for circuit redesign

Artificial intelligence techniques offer one possible avenue toward new CAD tools to handle the complexities of VLSI. Redesign is a Prototype knowledge-based system that uses Al techniques to interactively aid in the functional redesign of digital circuits. Given a desired change in the function of a circuit, Redesign combines rule-based knowledge of design tactics with its ability to analyse signal propagation through circuits, in order to help the user focus on an appropriate portion of the circuit to redesign, suggest local redesign alternatives, and determine side effects of possible redesigns. Using lessons learned from work on Redesign, we are working on systems to aid in designing and debugging VLSI.

Louis I. Steinberg

Papers

LEAP: a learning apprentice for VLSI design

A Knowledge-Based Approach to Design

Design as refinement plus constraint propagation: the VEXED experience

An intelligent aid for circuit redesign

The Redesign System: A Knowledge-Based Approach to VLSI CAD