This article argues that the agent-based computational model permits a distinctive approach to social science for which the term “generative ” is suitable. In defending this terminology, features distinguishing the approach from both “inductive ” and “deductive ” science are given. Then, the following specific contributions to social science are discussed: The agent-based computational model is a new tool for empirical research. It offers a natural environment for the study of connectionist phenomena in social science. Agent-based modeling provides a powerful way to address certain enduring—and especially interdisciplinary—questions. It allows one to subject certain core theories—such as neoclassical microeconomics—to important types of stress (e.g., the effect of evolving preferences). It permits one to study how rules of individual behavior give rise—or “map up”—to macroscopic regularities and organizations. In turn, one can employ laboratory behavioral research findings to select among competing agent-based (“bottom up”) models. The agent-based approach may well have the important effect of decoupling individual rationality from macroscopic equilibrium and of separating decision science from social science more generally. Agent-based modeling offers powerful new forms of hybrid theoretical-computational work; these are particularly relevant to the study of non-equilibrium systems. The agentbased approach invites the interpretation of society as a distributed computational device, and in turn the interpretation of social dynamics as a type of computation. This interpretation raises important foundational issues in social science—some related to intractability, and some to undecidability proper. Finally, since “emergence” figures prominently in this literature, I take up the connection between agent-based modeling and classical emergentism, criticizing the latter and arguing that the two are incompatible. � 1999 John Wiley &

Despite the widespread use of key concepts of the Neyman–Pearson (N–P) statistical paradigm—type I and II errors, significance levels, power, confidence levels—they have been the subject of philosophical controversy and debate for over 60 years. Both current and long-standing problems of N–P tests stem from unclarity and confusion, even among N–P adherents, as to how a test’s (pre-data) error probabilities are to be used for (post-data) inductive inference as opposed to inductive behavior. We argue that the relevance of error probabilities is to ensure that only statistical hypotheses that have passed severe or probative tests are inferred from the data. The severity criterion supplies a meta-statistical principle for evaluating proposed statistical inferences, avoiding classic fallacies from tests that are overly sensitive, as well as those not sensitive enough to particular errors and discrepancies.

www.hutter1.net Specialized intelligent systems can be found everywhere: finger print, handwriting, speech, and face recognition, spam filtering, chess and other game programs, robots, et al. This decade the first presumably complete mathematical theory of artificial intelligence based on universal induction-predictiondecision-action has been proposed. This information-theoretic approach solidifies the foundations of inductive inference and artificial intelligence. Getting the foundations right usually marks a significant progress and maturing of a field. The theory provides a gold standard and guidance for researchers working on intelligent algorithms. The roots of universal induction have been laid exactly half-a-century ago and the roots of universal intelligence exactly one decade ago. So it is timely to take stock of what has been achieved and what remains to be done. Since there are already good recent surveys, I describe the state-of-the-art only in passing and refer the reader to the literature.

The curve-fitting problem is often viewed as an exemplar which encapsulates the multitude of dimensions and issues associated with inductive inference, including underdetermination and the reliability of inference. The prevailing view is that the ‘fittest ’ curve is one which provides the optimal trade-off between goodness-of-fit and simplicity, with the Akaike Information Criterion (AIC) the preferred method. The paper argues that the AIC-type procedures do not provide an adequate solution to the curve fitting problem because (a) they have no criterion to assess when a curve captures the regularities in the data inadequately, and (b) they are prone to unreliable inferences. The thesis advocated is that for more satisfactory answers one needs to view the curvefitting problem in the context of error-statistical approach where (i) statistical adequacy provides a criterion for selecting the fittest curve and (ii) the error probabilities can be used to calibrate the reliability of inductive inference. This thesis is illustrated by comparing the Kepler and Ptolemaic models in terms of statistical adequacy, showing that the latter does not ‘save the phenomena ’ as often claimed. This calls into question the view concerning the pervasiveness of the problem of underdetermination; statistically adequate ‘fittest ’ curves are rare, not common. ∗Thanks are due to Deborah Mayo and Clark Glymour for valuable suggestions and comments on an earlier draft of the paper. 1 1

This paper introduces an initial account of a formal methodology for specification-based black-box verification testing of software artefacts against their specifications, as well as for validation testing of specifications against the so-called application concept [14]

In this position paper I consider four topics on which machine learning and philosophy of science can illuminate each other: scienti#c method, simplicity, theoretical terms and scienti#c realism. I conclude by stressing the di#erences between the two disciplines.

The nature of empirical simplicity and its relationship to scientific truth are long-standing puzzles. In this paper, empirical simplicity is explicated in terms of empirical effects, which are defined in terms of the structure of the inference problem addressed. Problem instances are classified according to the number of empirical effects they present. Simple answers are satisfied by simple worlds. An efficient solution achieves optimum worst-case cost over each complexity class with respect to such costs such as the number of retractions or errors prior to convergence and elapsed time to convergence. It is shown that always choosing the simplest theory compatible with experience and hanging onto it while it remains simplest is both necessary and sufficient for efficiency. 1 The Simplicity Puzzle Machine learning, statistics, and the philosophy of science all recommend the selection of simple theories or models on the basis of empirical data, where simplicity has something to do with minimizing independent entities, principles, causes, or equational coefficients. This intuitive preference for simplicity is called Ockham’s razor, after the fourteenth century theologian and logician William of Ockham, whose work exemplified a similar tendency. But in spite of its intuitive appeal, how could Ockham’s razor possibly help us find the true theory? For if we already know that the simplest theory is true or probably true, we don’t need Ockham’s razor to infer that it is. And if we don’t know that the simplest theory is true or probably true, how do we know that simplicity steers us in the right direction? It doesn’t help to say that simplicity is associated with other virtues such as testability (Popper 1968), unity (Friedman 1983), better explanations (Harman 1965), higher “confirmation ” (Carnap 1950, Glymour 1980), minimization of predictive risk (Akaike 1973), or minimum description length (Vitanyi and Li 2000), since if the truth weren’t simple, it wouldn’t have these nice properties either. To assume otherwise is to engage in wishful thinking (vanFraassen 1981). 1 Over-fitting arguments based upon minimization of predictive risk might seem to

What sorts of observations could confirm the universal hypothesis that all ravens are black? Carl Hempel proposed a number of simple and plausible principles which had the odd ("paradoxical") result that not only do observations of black ravens confirm that hypothesis, but so too do observations of yellow suns, green seas and white shoes. Hempel's response to his own paradox was to call it a psychological illusion--i.e., white shoes do indeed confirm that all ravens are black. Karl Popper on the other hand needed no response: he claimed that no observation can confirm any general statement--there is no such thing as confirmation theory. Instead, we should be looking for severe tests of our theories, strong attempts to falsify them. Bayesian philosophers have (in a loose sense) followed the Popperian analysis of Hempel's paradox (while retaining confirmation theory): they have usually judged that observing a white shoe in a shoe store does not qualify as a severe test of the hypothesis and so, while providing Bayesian confirmation, does so to only a minute degree. This rationalizes our common intuition of non-confirmation. All of these responses to the paradox are demonstrably wrong--granting an ordinary Bayesian measure of confirmation. A proper Bayesian analysis reveals that observations of white shoes may provide the raven hypothesis any degree of confirmation whatsoever.

The main aim of this paper is to revisit the curve-fitting problem using the reliability of inductive inference as a primary criterion for the ‘fittest ’ curve. Viewed from this perspective, it is argued that a crucial concern with the current framework for addressing the curve-fitting problem is, on the one hand, the undue influence of the mathematical approximation perspective, and on the other, the insufficient attention paid to the statistical modeling aspects of the problem. Using goodness-of-fit as the primary criterion for best, the mathematical approximation perspective undermines the reliability of inference objective by giving rise to selection rules which pay insufficient attention to ‘capturing the regularities in the data’. A more appropriate framework is offered by the error-statistical approach, where(i)statistical adequacy provides the criterion for assessing when a curve captures the regularities in the data adequately, and (ii) the relevant error probabilities canbeusedtoassessthereliabilityof inductive inference. Broadly speaking, the fittest curve (statistically adequate) is not determined by the smallness if its residuals, tempered by simplicity or other pragmatic criteria, but by the non-systematic (e.g. white-noise) nature of its residuals. The advocated error-statistical arguments are illustrated by comparing the Kepler and Ptolemaic models on empirical grounds. ∗ Forthcoming in Philosophy of Science, 2007. † I’m grateful to Deborah Mayo and Clark Glymour for many valuable suggestions and comments on an earlier draft of the paper; estimating the Ptolemaic model was the result of Glymour’s prompting and encouragement. 1 1

In science, one faces the problem of selecting the true theory from a range of alternative theories. The typical response is to select the simplest theory compatible with available evidence, on the authority of “Ockham’s Razor”. But how can a fixed bias toward simplicity help one find possibly complex truths? A short survey of standard answers to this question reveals them to be either wishful, circular, or irrelevant. A new explanation is presented, based on minimizing the reversals of opinion prior to convergence to the truth. According to this alternative approach, Ockham’s razor does not inform one which theory is true but is, nonetheless, the uniquely most efficient strategy for arriving at the true theory, where efficiency is a matter of minimizing reversals of opinion prior to finding the true theory. 1