ABSTRACTIn many applied sciences there is often a problem of revealing a structure underlyinga given collection of objects (situations, measurements, observations, etc.).A specific problem of this type is that of determining a hierarchy of meaningfulsubcategories in such a collection. This problem has been studied intensively inthe area of cluster analysis. The methods developed there, however, formulatesubcategories ('clusters') solely on the basis of pairwise 'similarity' (or 'proximity')of objects, and ignore the issue of the 'meaning' of the clusters obtained. Themethods do not provide any description of the clusters obtained. This paperpresents a method which constructs a hierarchy of subcategories, such that anappropriately generalized description of each subcategory is a single conjunctivestatement involving attributes of objects and has a simple conceptual interpretation.In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

Frogs and toads provide interesting parallels to the way in which humans can see the world about them, and use what they see in determining their actions. What they lack in subtlety of visually-guided behaviour, they make up for in the amenability of their behaviour and the underlying neural circuitry to experimental analysis. This paper presents three specific models of neural circuitry underlying visually-guided behaviour in frog and toad. They form an 'evolutionary sequence' in that each model incorporates its predecessor as a subsystem in such a way as to explain a wider range of behaviour data in a manner consistent with current neurophysiology and anatomy. The models thus form stages in the evolution of Rana computatrix, an increasingly sophisticated model of neural circuitry underlying the behaviour of the frog.In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

In Hayes, J. E., Michie, D., and Pao, Y.-H. (Eds.), Machine Intelligence 10. Ellis Horwood.

See also: Proceedings of the National Academy of Sciences USA 79, 2554-2558

"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.

Artificial Intelligence 19 (1), 17-37

AI research at CMU is closely integrated with other activities in the Computer Science Department, and to a major degree with ongoing research in the Psychology Department. Although there are over 50 faculty, staff and graduate students involved in various aspects of AI research, there is no administratively (or physically) separate AI laboratory. To underscore the interdisciplinary nature of our AI research, a significant fraction of the projects listed below are joint ventures between computer science and psychology.

Finally, abstraction can be extended to involve multiple complexity. In particular, one of the most costly behaviors levels, leading to a hierarchy of plans, each serving as a of the basic problem solving strategies is their inefficiency skeleton for the problem solving process at the next level in dealing with goal descriptions that include conjunctions. of detail. The search process at each level of detail can Because there is usually no good reason for the problem thus be reduced to a sequence of relatively simple solver to prefer to attack one conjunct before another, an subproblems of achieving the preconditions of the next incorrect ordering will often be chosen. This can lead to step in the skeleton plan from an initial state in which the an extensive search for a sequence of actions to try to previous step in the skeleton plan has just been achieved.

Biological Cybernetics, 40 (3), 201-11

In IJCAI-81, pp. 67–69.