A measure of search difficulty, fitness distance correlation (FDC), is introduced and examined in relation to genetic algorithm (GA) performance. In many cases, this correlation can be used to predict the performance of a GA on problems with known global maxima. It correctly classifies easy deceptive problems as easy and difficult non-deceptive problems as difficult, indicates when Gray coding will prove better than binary coding, and is consistent with the surprises encountered when GAs were used on the Tanese and royal road functions. The FDC measure is a consequence of an investigation into the connection between GAs and heuristic search. 1 INTRODUCTION A correspondence between evolutionary algorithms and heuristic state space search is developed in (Jones, 1995b). This is based on a model of fitness landscapes as directed, labeled graphs that are closely related to the state spaces employed in heuristic search. We examine one aspect of this correspondence, the relationship between...

We describe an emerging field, that of nonclassical computability and nonclassical computing machinery. According to the nonclassicist, the set of well-defined computations is not exhausted by the computations that can be carried out by a Turing machine. We provide an overview of the field and a philosophical defence of its foundations.

Quantum theory has found a new field of applications in the realm of information and computation during the recent years. This paper reviews how quantum physics allows information coding in classically unexpected and subtle nonlocal ways, as well as information processing with an efficiency largely surpassing that of the present and foreseeable classical computers. Some outstanding aspects of classical and quantum information theory will be addressed here. Quantum teleportation, dense coding, and quantum cryptography are discussed as a few samples of the impact of quanta in the transmission of information. Quantum logic gates and quantum algorithms are also discussed as instances of the improvement in information processing by a quantum computer. We provide finally some examples of current experimental

This paper introduces a new analysis tool called reverse hillclimbing, and demonstrates how it can be used to evaluate the performance of a genetic algorithm. Using reverse hillclimbing, one can calculate the exact probability that hillclimbing will attain some point in a landscape. From this, the expected number of evaluations before the point is found by hillclimbing can be calculated. This figure can be compared to the average number of evaluations done by a genetic algorithm. This procedure is illustrated using the Busy Beaver problem, an interesting problem of theoretical importance in its own right. At first sight, a genetic algorithm appears to perform very well on this landscape, after examining only a vanishingly small proportion of the space. Closer examination reveals that the number of evaluations it performs to discover an optimal solution compares poorly with even the simplest form of hillclimbing. Finally, several other uses for reverse hillclimbing are discussed. 3 San...

This paper surveys a wide range of proposed hypermachines, examining the resources that they require and the capabilities that they possess.

The dominant scientific and philosophical view of the mind --- according to which, put starkly, cognition is computation --- is refuted herein, via specification and defense of the following new argument: Computation is reversible; cognition isn't; ergo, cognition isn't computation. After presenting a sustained dialectic arising from this defense, we conclude with a brief preview of the view we would put in place of the cognition-is-computation doctrine. We are indebted to Bill Rapaport, Pat Hayes, Ken Ford, Marvin Minsky, Jim Fahey, two anonymous referees (who provided particularly insightful comments), and many Rensselaer students. These people provided trenchant objections which saw to the evolution of the present version from a rather inauspicious primogenitor. 1 Introduction The dominant scientific and philosophical view of the mind --- put starkly, that cognition is computation --- is refuted herein, via specification and defense of the following new argument: Computation is...

Inspection of the current literature on Design Patterns shows that the Prime Directive for this community is Pragmatics. It hardly matters what patterns are, or how Patterns are represented formally or syntactically. What does matter is their role in enhancing the reuse of good solutions to recurring problems. In this article I want to show that minimal assumptions about the pragmatic use of Patterns suffice to show that Design Patterns form just another formal language, which can be shown to be at least Recursively enumerable. Whether the language is Recursive depends on further conditions on the actual relation which is assumed to hold between a pattern and its possible invocations. There are no a priori reasons enforcing that this should be an easily decidable relation; quite to the contrary: a little amount of linguistic expressivity suffices for showing that this relation is likely to be complex. Without restrictions on the linguistic tools allowed for expressing design patterns t...

Genetic algorithms (GAs) and heuristic search are shown to be structurally similar. The strength of the correspondence and its practical consequences are demonstrated by considering the relationship between fitness functions in GAs and the heuristic functions of AI. By examining the extent to which fitness functions approximate an AI ideal, a measure of GA search difficulty is defined and applied to previously studied problems. The success of the measure in predicting GA performance (1) illustrates the potential advantages of viewing evolutionary search from a heuristic search perspective and (2) appears to be an important step towards answering a question that has been the subject of much research in the GAs community: what makes search hard (or easy) for a GA? Submitted to the International Joint Conference on Artificial Intelligence. 1 Introduction The primary aim of this paper is to establish a connection between genetic algorithms (GAs) and heuristic search. The foundation of t...

To a majority of the people involved in the study of expertise from a computational perspective, `expertise' tends to refer to domains such as medical diagnosis, aircraft piloting, auditing, etc. The reasoning in domains like these appears to be ready-made for computational packaging. But what if we try to cast a broader, braver net in an attempt to catch varieties of expertise out there in the real world which don't, at least at first glance, look like they can be rendered in computational terms? In particular, what about mathematical expertise? In this chapter I focus on elementary "infinitary " expertise in the domain of mathematical logic. I argue that at least some of this expertise is indeed uncomputable. I end by briefly discussing the implications of this argument for the practice of AI and expert systems.

Various computationally-based efforts have been made by numerous groups to conquer Rado’s Σ function (the “Busy Beaver ” problem): brute force searches, genetic algorithms, heuristic behaviour analyses, etc. These efforts have been successful only for a very small inputs to the function and they each have focused on only one sub-formulation of the problem. The present paper proposes and explores the merits of a tree-based search approach to the solving the problem utilising a set of optimisation techniques extending the domain for