ion-Partitioned Evaluator (APE) architecture which has been tested in a simulated, single-agent, indoor navigation domain [SH90]. The APE architecture is composed of a number of concurrent, hierarchically abstract action control layers, each representing and reasoning about some particular aspect of the agent's task domain. Implemented as a parallel blackboard-based planner, the five layers --- sensor/motor, spatial, temporal, causal, and conventional (general knowledge) --- effectively partition the agent's data processing duties along a number of dimensions including temporal granularity, information/resource use, and functional abstraction. Perceptual information flows strictly from the agent sensors (connected to the sensor /motor level) toward the higher levels, while command or goal-achievement information flows strictly downward towards the agent's effectors (also connected to the sensor/motor level). Besides mechanisms for communicating with other layers, each layer in the AP...

A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.

Spatializations are computer visualizations in which nonspatial information is depicted spatially. Spatializations of large databases commonly use distance as a metaphor to depict semantic (nonspatial) similarities among data items. By analogy to the "first law of geography", which states that closer things tend to be more similar, we propose a "first law of cognitive geography," which states that people believe closer things are more similar. In this paper, we present two experiments that investigate the validity of the first law of cognitive geography as applied to the interpretation of "point-display spatializations." Point displays depict documents (or other information-bearing entities) as 2- or 3-dimensional collections of points. Our results largely support the first law of cognitive geography and enrich it by identifying different types of distance that may be metaphorically related to similarity. We also identify characteristics of point displays other than distance relationships that influence similarity judgments.

Accelerated Turing machines are Turing machines that perform tasks commonly regarded as impossible, such as computing the halting function. The existence of these notional machines has obvious implications concerning the theoretical limits of computability. 2 1. Introduction Neither Turing nor Post, in their descriptions of the devices we now call Turing machines, made much mention of time (Turing 1936, Post 1936). 1 They listed the primitive operations that their devices perform - read a square of the tape, write a single symbol on a square of the tape (first deleting any symbol already present), move one square to the right, and so forth - but they made no mention of the duration of each primitive operation. The crucial concept is that of whether or not the machine halts after a finite number of operations. Temporal considerations are not relevant to the functioning of the devices as described, nor - so we are clearly supposed to believe - to the soundness of the proofs that Turi...

A myth has arisen concerning Turing's paper of 1936, namely that Turing set forth a fundamental principle concerning the limits of what can be computed by machine - a myth that has passed into cognitive science and the philosophy of mind, to wide and pernicious effect. This supposed principle, sometimes incorrectly termed the 'Church-Turing thesis', is the claim that the class of functions that can be computed by machines is identical to the class of functions that can be computed by Turing machines. In point of fact Turing himself nowhere endorses, nor even states, this claim (nor does Church). I describe a number of notional machines, both analogue and digital, that can compute more than a universal Turing machine. These machines are exemplars of the class of nonclassical computing machines. Nothing known at present rules out the possibility that machines in this class will one day be built, nor that the brain itself is such a machine. These theoretical considerations undercut a numb...

This paper is a survey of a large number of informal definitions of “intelligence” that the authors have collected over the years. Naturally, compiling a complete list would be impossible as many definitions of intelligence are buried deep inside articles and books. Nevertheless, the 70-odd definitions presented here are, to the authors ’ knowledge, the largest and most well referenced collection there is.

We live in an era when everyday activities are shaped by environments that are not only artificial—almost half of humanity lives in cities—but also mediated. Emotional and cognitive activities in all levels and segments of society are increasingly vested in information-rich venues supported by television, radio, telephone, and computer networks. Even in very remote areas, hunters and farmers watch satellite broadcasts and play battery-operated video games. And in the depths of the Amazon River basin, tribes use tiny video cameras to document territorial encroachments and destruction of rain forest habitat. 10.1 OVERVIEW This chapter explores the metaphor of media as lived environments. A medium can be considered an environment to the extent that it supports both the perception of opportunities for acting and some means for acting. This environmental metaphor can help us understand how media users exercise their powers of perception, mobility, and agency within the constraints

Although Measures of Effectiveness (MOEs) are an important element of the Systems Engineering process, they have yet to gain acceptance from practitioners. This is caused not only by the confusion surrounding their definition but also the perceived difficulty in formulating appropriate MOEs. This paper builds on previously published papers that address the issue of the definition of MOEs and the distinction to be drawn with Measures of Performance. Following a brief review of this existing work, a process for formulating MOEs is suggested and explained. This is supplemented by several examples from everyday life and from historical references. The examples build on the issues raised in the discussion of the process and provide practical examples to reinforce what has been previously discussed. © 2002 Commonwealth of Australia. Exclusive worldwide publication rights in the article have been transferred to Wiley Periodicals, Inc. Syst Eng 5, 253–263, 2002 Key words: measures of effectiveness; measures of performance; critical operational issues; viewpoints; effectiveness.

Within this paper, we present an approach to evaluate the skillfulness of robot behaviour and the progress made by robots when learning new and adapting existing skills.

This paper outlines a framework for analyzing how decision makers achieve “situation awareness ” in complex, dynamic and uncertain situations. We use this framework to analyze a typical case of human “error ” in the command and control of a complex system. Our analysis shows that decision errors in this and other cases can be characterized as “normal ” (i.e., rational) consequences of the decision makers’ mental models. We conclude by suggesting that a mental models approach can provide unifying insights into the “heuristics and biases ” proposed by previous researchers. _____________________________________________________________________________________________ 1