We show how to estimate (1) the number of functions that can be implemented by a particular network architecture, (2) how much analog precision is needed in the connections in the network, and (3) the number of training examples the network must see before it can be expected to form reliable generalizations.

We show how to estimate (1) the number of functions that can be implemented by a particular network architecture, (2) how much analog precision is needed in the connections inthe network, and (3) the number of training examples the network must see before it can be expected to form reliable generalizations.

"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." Machine Learning, 1 (1), 47–80.

In AAAI-84, pp. 251–254.

Machine learning has always been an integral part of artificial intelligence, and its methodology has evolved in concert with the major concerns of the field. In response to the difficulties of encoding ever-increasing volumes of knowledge in modern AI systems, many researchers have recently turned their attention to machine learning as a means to overcome the knowledge acquisition bottleneck. This article presents a taxonomic analysis of machine learning organized primarily by learning strategies and secondarily by knowledge representation and application areas. A historical survey outlining the development of various approaches to machine learning is presented from early neural networks to present knowledge-intensive techniques.

"The purpose of this paper is to compare various approaches to generalization in terms of a single framework. Toward this end, generalization is cast as a search problem, and alternative methods for generalization are characterized in terms of the search strategies that they employ. This characterization uncovers similarities among approaches, and leads to a comparison of relative capabilities and computational complexities of alternative approaches. The characterization allows a precise comparison of systems that utilize different representations for learned generalizations."Artificial Intelligence, 18 (2), 203-26.

"The terms adaptation, learning, concept-formation, induction, self-organization, and self-repair have all been used in the context of learning system (LS) research. The research has been conducted within many different scientific communities, however, and these terms have come to have a variety of meanings. It is therefore often difficult to recognize that problems which are described differently may in fact be identical. Learning system models as well are often tuned to the require- ments of a particular discipline and are not suitable for application in related disciplines."In Encyclopedia of Computer Science and Technology, Vol. 11. Dekker

"An important research problem in artificial intelligence is the study of methods for learning general concepts or rules from a set of training instances. An approach to this problem is presented which is guaranteed to find, without backtracing, all rule versions consistent with a set of positive and negative training instances. The algorithm put forth uses a representation of the space of those rules consistent with the observed training data. This "rule version space" is modified in response to new training instances by eliminating candidate rule versions found to conflict with each new instance. The use of version spaces is discussed in the context of Meta-DENDRAL, a program which learns rules in the domain of chemical spectroscopy."Proc. IJCAI 77 VOL 1 MASSACHUSETTS INSTITUTE OF TECHNOLOGY CAMBRIDGE, MASSACHUSETTS, USA AUGUST 22 - 25 , 1977, pp.305-310

This paper investigates the problem of implementing machine learning of heuristics. First, a method of representing heuristics as production rules is developed which facilitates dynamic manipulation of the heuristics by the program embodying them. Second, procedures are developed which permit a problem-solving program employing heuristics in production rule form to learn to improve its performance by evaluating and modifying existing heuristics and hypothesizing new ones, either during an explicit training process or during normal program operation. Third, the feasibility of these ideas in a complex problem-solving situation is demonstrated by using them in a program to make the bet decision in draw poker. Finally, problems which merit further investigation are discussed, including the problem of defining the task environment and the problem of adapting the system to board games.