Abstract. An architecture is described for designing systems that acquire and manipulate large amounts of unsystematized, or so-called commonsense, knowledge. Its aim is to exploit to the full those aspects of computational learning that are known to offer powerful solutions in the acquisition and maintenance of robust knowledge bases. The architecture makes explicit the requirements on the basic computational tasks that are to be performed and is designed to make these computationally tractable even for very large databases. The main claims are that (i) the basic learning and deduction tasks are provably tractable and (ii) tractable learning offers viable approaches to a range of issues that have been previously identified as problematic for artificial intelligence systems that are programmed. Among the issues that learning offers to resolve are robustness to inconsistencies, robustness to incomplete information and resolving among alternatives. Attribute-efficient learning algorithms, which allow learning from few examples in large dimensional systems, are fundamental to the approach. Underpinning the overall architecture is a new principled approach to manipulating relations in learning systems. This approach, of independently quantified arguments, allows propositional learning algorithms to be applied systematically to learning relational concepts in polynomial time and in a modular fashion.

Suppose that we wish to learn from examples and counter-examples a criterion for recognizing whether an assembly of wooden blocks constitutes an arch. Suppose also that we have preprogrammed recognizers for various relationships e.g. on-top-of(x; y), above(x; y), etc. and believe that some possibly complex expression in terms of these base relationships should suffice to approximate the desired notion of an arch. How can we formulate such a relational learning problem so as to exploit the benefits that are demonstrably available in propositional learning, such as attribute-efficient learning by linear separators, and error-resilient learning? We believe that learning in a general setting that allows for multiple objects and relations in this way is a fundamental key to resolving the following dilemma that arises in the design of intelligent systems: Mathematical logic is an attractive language of description because it has clear semantics and sound proof procedures. However, as a basis for large programmed systems it leads to brittleness because, in practice, consistent usage of the various predicate names throughout a system cannot be guaranteed, except in application areas such as mathematics where the viability of the axiomatic method has been demonstrated independently. In this paper we develop the following approach to circumventing this dilemma. We suggest that brittleness can be overcome by using a new kind of logic in which each statement is learnable. By allowing the system to learn rules empirically from the environment, relative to any particular programs it may have for recognizing some base predicates, we enable the system to acquire a set of statements approximately consistent with each other and with the world, without the need for a globally knowledgeable and consistent programmer. We illustrate

What are the most important problems of computational intelligence? A sketch of the road to intelligent systems is presented. Several experts have made interesting comments on the most challenging problems.

Abstract not found

Keywords: POP-II.B. program comprehension, POP-V.A. short-term memory Program comprehension is perhaps one of the oldest topics within the psychology of programming. It addresses a central issue: how programmers work with and manipulate source code to construct effective software systems. Models can play an important role in understanding the challenges developers and engineers contend with. This paper presents a model of program comprehension, or code cognition, which has been derived from literature found within the disciplines of computing and psychology. Drawing on direct experimentation, this paper argues that a model of code cognition should take account of the visual, spatial and linguistic abilities of developers. The strengths and weaknesses of this model are discussed and further research directions presented. 1.

The effects of repeating a task-irrelevant element and inserting intervening trials between the last prime and the probe trial in a negative priming study were compared with a standard prime/probe pair. An associative model based on SAC (e.g. Reder & Schunn, 1996; Schunn, Reder, Nhouyvanisvong, Richards, & Stroffolino, 1997) was able to account for both the decrease in response times across the repeated primes and the increase in response times when the task-irrelevant element became relevant. Introduction Until recently, theories of attention have focused on the object of attention. These theories emphasized the facilitatory "spotlight" at the center of attention, and the remaining areas of visual space were largely ignored (e.g., Broadbent, 1958; Shiffrin & Schneider, 1977). Over the past several years, however, researchers have developed evidence of an inhibitory effect of attention on objects that fall outside the spotlight. In particular, if some part of a visual display...