The aim of this paper is to sketch a theory of justified belief. What I have in mind is an explanatory theory, one that explains in a general way why certain beliefs are counted as justified and others as unjustified. Unlike some traditional approaches, I do not try to prescribe standards for justification that differ from, or improve upon, our ordinary standards. I merely try to explicate the ordinary standards, which are, I believe, quite different from those of many classical, (...) e. g., ‘Cartesian’, accounts. (shrink)

Hunting Causes and Using Them argues that causation is not one thing, as commonly assumed, but many. There is a huge variety of causal relations, each with different characterizing features, different methods for discovery and different uses to which it can be put. In this collection of new and previously published essays, Nancy Cartwright provides a critical survey of philosophical and economic literature on causality, with a special focus on the currently fashionable Bayes-nets and invariance methods - and it exposes (...) a huge gap in that literature. Almost every account treats either exclusively how to hunt causes or how to use them. But where is the bridge between? It's no good knowing how to warrant a causal claim if we don't know what we can do with that claim once we have it. This book will interest philosophers, economists and social scientists. (shrink)

In the international bestseller, Thinking, Fast and Slow, Daniel Kahneman, the renowned psychologist and winner of the Nobel Prize in Economics, takes us on a groundbreaking tour of the mind and explains the two systems that drive the way we think. System 1 is fast, intuitive, and emotional; System 2 is slower, more deliberative, and more logical. The impact of overconfidence on corporate strategies, the difficulties of predicting what will make us happy in the future, the profound effect of cognitive (...) biases on everything from playing the stock market to planning our next vacation—each of these can be understood only by knowing how the two systems shape our judgments and decisions. -/- Engaging the reader in a lively conversation about how we think, Kahneman reveals where we can and cannot trust our intuitions and how we can tap into the benefits of slow thinking. He offers practical and enlightening insights into how choices are made in both our business and our personal lives—and how we can use different techniques to guard against the mental glitches that often get us into trouble. Winner of the National Academy of Sciences Best Book Award and the Los Angeles Times Book Prize and selected by The New York Times Book Review as one of the ten best books of 2011, Thinking, Fast and Slow is destined to be a classic. (shrink)

This is the classic work upon which modern-day game theory is based. What began as a modest proposal that a mathematician and an economist write a short paper together blossomed, when Princeton University Press published Theory of Games and Economic Behavior. In it, John von Neumann and Oskar Morgenstern conceived a groundbreaking mathematical theory of economic and social organization, based on a theory of games of strategy. Not only would this revolutionize economics, but the entirely new field of scientific inquiry (...) it yielded--game theory--has since been widely used to analyze a host of real-world phenomena from arms races to optimal policy choices of presidential candidates, from vaccination policy to major league baseball salary negotiations. And it is today established throughout both the social sciences and a wide range of other sciences. (shrink)

Science is the study of our world, as it is in its messy reality. Nonetheless, science requires idealization to function—if we are to attempt to understand the world, we have to find ways to reduce its complexity. Idealization and the Aims of Science shows just how crucial idealization is to science and why it matters. Beginning with the acknowledgment of our status as limited human agents trying to make sense of an exceedingly complex world, Angela Potochnik moves on to explain (...) how science aims to depict and make use of causal patterns—a project that makes essential use of idealization. She offers case studies from a number of branches of science to demonstrate the ubiquity of idealization, shows how causal patterns are used to develop scientific explanations, and describes how the necessarily imperfect connection between science and truth leads to researchers’ values influencing their findings. The resulting book is a tour de force, a synthesis of the study of idealization that also offers countless new insights and avenues for future exploration. (shrink)

A new approach for defining causality and such related notions as degree of responsibility, degrees of blame, and causal explanation. Causality plays a central role in the way people structure the world; we constantly seek causal explanations for our observations. But what does it even mean that an event C "actually caused" event E? The problem of defining actual causation goes beyond mere philosophical speculation. For example, in many legal arguments, it is precisely what needs to be established in order (...) to determine responsibility. The philosophy literature has been struggling with the problem of defining causality since Hume. In this book, Joseph Halpern explores actual causality, and such related notions as degree of responsibility, degree of blame, and causal explanation. The goal is to arrive at a definition of causality that matches our natural language usage and is helpful, for example, to a jury deciding a legal case, a programmer looking for the line of code that cause some software to fail, or an economist trying to determine whether austerity caused a subsequent depression. Halpern applies and expands an approach to causality that he and Judea Pearl developed, based on structural equations. He carefully formulates a definition of causality, and building on this, defines degree of responsibility, degree of blame, and causal explanation. He concludes by discussing how these ideas can be applied to such practical problems as accountability and program verification. Technical details are generally confined to the final section of each chapter and can be skipped by non-mathematical readers. (shrink)

We are sceptical of concerns over the opacity of algorithmic decision tools. While transparency and explainability are certainly important desiderata in algorithmic governance, we worry that automated decision-making is being held to an unrealistically high standard, possibly owing to an unrealistically high estimate of the degree of transparency attainable from human decision-makers. In this paper, we review evidence demonstrating that much human decision-making is fraught with transparency problems, show in what respects AI fares little worse or better and argue that (...) at least some regulatory proposals for explainable AI could end up setting the bar higher than is necessary or indeed helpful. The demands of practical reason require the justification of action to be pitched at the level of practical reason. Decision tools that support or supplant practical reasoning should not be expected to aim higher than this. We cast this desideratum in terms of Daniel Dennett’s theory of the “intentional stance” and argue that since the justification of action for human purposes takes the form of intentional stance explanation, the justification of algorithmic decisions should take the same form. In practice, this means that the sorts of explanations for algorithmic decisions that are analogous to intentional stance explanations should be preferred over ones that aim at the architectural innards of a decision tool. (shrink)

Woodward's long awaited book is an attempt to construct a comprehensive account of causation explanation that applies to a wide variety of causal and explanatory claims in different areas of science and everyday life. The book engages some of the relevant literature from other disciplines, as Woodward weaves together examples, counterexamples, criticisms, defenses, objections, and replies into a convincing defense of the core of his theory, which is that we can analyze causation by appeal to the notion of manipulation.

A number of writers, myself included, have recently argued that an “interventionist” treatment of causation of the sort defended in Woodward, 2003 can be used to cast light on so-called “causal exclusion” arguments. This interventionist treatment of causal exclusion has in turn been criticized by other philosophers. This paper responds to these criticisms. It describes an interventionist framework for thinking about causal relationships when supervenience relations are present. I contend that this framework helps us to see that standard arguments for (...) causal exclusion involve mistaken assumptions about what it is appropriate to control for or hold fixed in assessing causal claims. The framework also provides a natural way of capturing the idea that properties that supervene on but that are not identical with realizing properties can be causally efficacious. (shrink)

This paper attempts to elucidate three characteristics of causal relationships that are important in biological contexts. Stability has to do with whether a causal relationship continues to hold under changes in background conditions. Proportionality has to do with whether changes in the state of the cause “line up” in the right way with changes in the state of the effect and with whether the cause and effect are characterized in a way that contains irrelevant detail. Specificity is connected both to (...) David Lewis’ notion of “influence” and also with the extent to which a causal relation approximates to the ideal of one cause–one effect. Interrelations among these notions and their possible biological significance are also discussed. (shrink)

I defend an account of explanatory depth according to which explanations in the non-fundamental sciences can be deeper than explanations in fundamental physics.

Within the causal modeling literature, debates about the Causal Faithfulness Condition have concerned whether it is probable that the parameters in causal models will have values such that distinct causal paths will cancel. As the parameters in a model are fixed by the probability distribution over its variables, it is initially puzzling what it means to assign probabilities to these parameters. I propose that to assign a probability to a parameter in a model is to treat that parameter as a (...) function of a variable in an augmented model. By combining this proposal with widely adopted principles regarding which variables must be included in a model, I argue that the various proposed counterexamples to CFC involving coordinated parameters are not genuine counterexamples. I then consider the cases in which CFC fails due not to coordination, but by coincidence, and propose explanatory and predictive bases for ruling out such coincidences without presuming that they are improbable. The aim of the proposed defenses is not to show that CFC never fails, but rather to argue that its use in a particular context may be defended using general modeling assumptions rather than by relying on claims about how often it fails. (shrink)

Artificial intelligence has historically been conceptualized in anthropomorphic terms. Some algorithms deploy biomimetic designs in a deliberate attempt to effect a sort of digital isomorphism of the human brain. Others leverage more general learning strategies that happen to coincide with popular theories of cognitive science and social epistemology. In this paper, I challenge the anthropomorphic credentials of the neural network algorithm, whose similarities to human cognition I argue are vastly overstated and narrowly construed. I submit that three alternative supervised learning (...) methods—namely lasso penalties, bagging, and boosting—offer subtler, more interesting analogies to human reasoning as both an individual and a social phenomenon. Despite the temptation to fall back on anthropomorphic tropes when discussing AI, however, I conclude that such rhetoric is at best misleading and at worst downright dangerous. The impulse to humanize algorithms is an obstacle to properly conceptualizing the ethical challenges posed by emerging technologies. (shrink)

Recent years have seen a surge in online collaboration between experts and amateurs on scientific research. In this article, we analyse the epistemological implications of these crowdsourced projects, with a focus on Zooniverse, the world’s largest citizen science web portal. We use quantitative methods to evaluate the platform’s success in producing large volumes of observation statements and high impact scientific discoveries relative to more conventional means of data processing. Through empirical evidence, Bayesian reasoning, and conceptual analysis, we show how information (...) and communication technologies enhance the reliability, scalability, and connectivity of crowdsourced e-research, giving online citizen science projects powerful epistemic advantages over more traditional modes of scientific investigation. These results highlight the essential role played by technologically mediated social interaction in contemporary knowledge production. We conclude by calling for an explicitly sociotechnical turn in the philosophy of science that combines insights from statistics and logic to analyse the latest developments in scientific research. (shrink)

Scientific understanding, this paper argues, can be analyzed entirely in terms of a mental act of “grasping” and a notion of explanation. To understand why a phenomenon occurs is to grasp a correct explanation of the phenomenon. To understand a scientific theory is to be able to construct, or at least to grasp, a range of potential explanations in which that theory accounts for other phenomena. There is no route to scientific understanding, then, that does not go by way of (...) scientific explanation. (shrink)

Causal accounts of scientific explanation are currently broadly accepted (though not universally so). My first task in this paper is to show that, even for a causal approach to explanation, significant features of explanatory practice are not determined by settling how causal facts bear on the phenomenon to be explained. I then develop a broadly causal approach to explanation that accounts for the additional features that I argue an explanation should have. This approach to explanation makes sense of several aspects (...) of actual explanatory practice, including the widespread use of equilibrium explanations, the formulation of distinct explanations for a single event, and the tight relationship between explanations of events and explanations of causal regularities. (shrink)

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the purpose of providing an explanation of a model or a decision is to make it understandable to its stakeholders. But without a previous grasp of what it means to say that an agent understands a model or a decision, the explanatory strategies will (...) lack a well-defined goal. Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models, and to focus instead on the pragmatic conditions that determine the best fit between a model and the methods and devices deployed to understand it. After an examination of the different types of understanding discussed in the philosophical and psychological literature, I conclude that interpretative or approximation models not only provide the best way to achieve the objectual understanding of a machine learning model, but are also a necessary condition to achieve post hoc interpretability. This conclusion is partly based on the shortcomings of the purely functionalist approach to post hoc interpretability that seems to be predominant in most recent literature. (shrink)

In this paper I argue that the search for explainable models and interpretable decisions in AI must be reformulated in terms of the broader project of offering a pragmatic and naturalistic account of understanding in AI. Intuitively, the purpose of providing an explanation of a model or a decision is to make it understandable to its stakeholders. But without a previous grasp of what it means to say that an agent understands a model or a decision, the explanatory strategies will (...) lack a well-defined goal. Aside from providing a clearer objective for XAI, focusing on understanding also allows us to relax the factivity condition on explanation, which is impossible to fulfill in many machine learning models, and to focus instead on the pragmatic conditions that determine the best fit between a model and the methods and devices deployed to understand it. After an examination of the different types of understanding discussed in the philosophical and psychological literature, I conclude that interpretative or approximation models not only provide the best way to achieve the objectual understanding of a machine learning model, but are also a necessary condition to achieve post hoc interpretability. This conclusion is partly based on the shortcomings of the purely functionalist approach to post hoc interpretability that seems to be predominant in most recent literature. (shrink)

This article considers the popular thesis that a more proportional relationship between a cause and its effect yields a more abstract causal explanation of that effect, which in turn produces a deeper explanation. This thesis is taken to have important implications for choosing the optimal granularity of explanation for a given explanandum. In this article, I argue that this thesis is not generally true of probabilistic causal relationships. In light of this finding, I propose a pragmatic, interest-relative measure of explanatory (...) depth. This measure uses a decision-theoretic model of information pricing to determine the optimal granularity of explanation for a given explanandum, agent, and decision problem. (shrink)

Recently, several authors have argued that scientific understanding should be a new topic of philosophical research. In this article, I argue that the three most developed accounts of understanding--Grimm's, de Regt's, and de Regt and Dieks's--can be replaced by earlier accounts of scientific explanation without loss. Indeed, in some cases, such replacements have clear benefits.

Ockham’s razor is the characteristic scientific penchant for simpler, more testable, and more unified theories. Glymour’s early work on confirmation theory eloquently stressed the rhetorical plausibility of Ockham’s razor in scientific arguments. His subsequent, seminal research on causal discovery still concerns methods with a strong bias toward simpler causal models, and it also comes with a story about reliability—the methods are guaranteed to converge to true causal structure in the limit. However, there is a familiar gap between convergent reliability and (...) scientific rhetoric: convergence in the long run is compatible with any conclusion in the short run. For that reason, Carnap suggested that the proper sense of reliability for scientific inference should lie somewhere between short-run reliability and mere convergence in the limit. One natural such concept is straightest possible convergence to the truth, where straightness is explicated in terms of minimizing reversals of opinion and cycles of opinion prior to convergence. We close the gap between scientific rhetoric and scientific reliability by showing that Ockham’s razor is necessary for cycle-optimal convergence to the truth, and that patiently waiting for information to resolve conflicts among simplest hypotheses is necessary for reversal-optimal convergence to the truth. (shrink)

It it tempting to think that if an outcome had some probability of not occurring, then we cannot explain why that outcome in fact occurred. Despite this intuition, most philosophers of science have come to admit the possibility of indeterministic explanation. Yet some of them continue to hold that if an outcome was not determined, it cannot be explained why that outcome rather than some other occurred. I argue that this is an untenable compromise: if indeterministic explanation is possible, then (...) indeterministic contrastive explanation is possible too. In order to defend this conclusion, I develop an account of contrastive explanation. (shrink)

expose some gaps and difficulties in the argument for the causal Markov condition in our essay ‘Independence, Invariance and the Causal Markov Condition’ ([1999]), and we are grateful for the opportunity to reformulate our position. In particular, Cartwright disagrees vigorously with many of the theses we advance about the connection between causation and manipulation. Although we are not persuaded by some of her criticisms, we shall confine ourselves to showing how our central argument can be reconstructed and to casting doubt (...) on Cartwright's claim that the causal Markov condition typically fails when there are indeterministic by-products. Why believe the causal Markov condition? Causation and manipulation The argument Indeterministic by-products and the causal Markov condition The chemical factory counterexample and PM2 Conclusions: causation and manipulability. (shrink)

Among philosophers of science there seems to be a general consensus that understanding represents a species of knowledge, but virtually every major epistemologist who has thought seriously about understanding has come to deny this claim. Against this prevailing tide in epistemology, I argue that understanding is, in fact, a species of knowledge: just like knowledge, for example, understanding is not transparent and can be Gettiered. I then consider how the psychological act of "grasping" that seems to be characteristic of understanding (...) differs from the sort of psychological act that often characterizes knowledge. Zagzebski's account Kvanvig's account Two problems Comanche cases Unreliable sources of information The upper-right quadrant So is understanding a species of knowledge? A false choice. (shrink)

Russian translation of Gettier E. L. Is Justified True Belief Knowledge? // Analysis, vol. 23, 1963. Translated by Lev Lamberov with kind permission of the author.

The interventionist account of causal explanation, in the version presented by Jim Woodward, has been recently claimed capable of buttressing the widely felt—though poorly understood—hunch that high-level, relatively abstract explanations, of the sort provided by sciences like biology, psychology and economics, are in some cases explanatorily optimal. It is the aim of this paper to show that this is mistaken. Due to a lack of effective constraints on the causal variables at the heart of the interventionist causal-explanatory scheme, as presently (...) formulated it is either unable to prefer high-level explanations to low, or systematically overshoots, recommending explanations at so high of a level as to be virtually vacuous. (shrink)

Agents require a constant flow, and a high level of processing, of relevant semantic information, in order to interact successfully among themselves and with the environment in which they are embedded. Standard theories of information, however, are silent on the nature of epistemic relevance. In this paper, a subjectivist interpretation of epistemic relevance is developed and defended. It is based on a counterfactual and metatheoretical analysis of the degree of relevance of some semantic information i to an informee/agent a, as (...) a function of the accuracy of i understood as an answer to a query q, given the probability that q might be asked by a. This interpretation of epistemic relevance vindicates a strongly semantic theory of information, according to which semantic information encapsulates truth. It accounts satisfactorily for several important applications and interpretations of the concept of relevant information in a variety of philosophical areas. And it interfaces successfully with current philosophical interpretations of causal and logical relevance. (shrink)

Luciano Floridi presents a book that will set the agenda for the philosophy of information. PI is the philosophical field concerned with the critical investigation of the conceptual nature and basic principles of information, including its dynamics, utilisation, and sciences, and the elaboration and application of information-theoretic and computational methodologies to philosophical problems. This book lays down, for the first time, the conceptual foundations for this new area of research. It does so systematically, by pursuing three goals. Its metatheoretical goal (...) is to describe what the philosophy of information is, its problems, approaches, and methods. Its introductory goal is to help the reader to gain a better grasp of the complex and multifarious nature of the various concepts and phenomena related to information. Its analytic goal is to answer several key theoretical questions of great philosophical interest, arising from the investigation of semantic information. (shrink)

In this article, I outline a logic of design of a system as a specific kind of conceptual logic of the design of the model of a system, that is, the blueprint that provides information about the system to be created. In section two, I introduce the method of levels of abstraction as a modelling tool borrowed from computer science. In section three, I use this method to clarify two main conceptual logics of information inherited from modernity: Kant’s transcendental logic (...) of conditions of possibility of a system, and Hegel’s dialectical logic of conditions of in/stability of a system. Both conceptual logics of information analyse structural properties of given systems. Strictly speaking, neither is a conceptual logic of information about the conditions of feasibility of a system, that is, neither is a logic of information as a logic of design. So, in section four, I outline this third conceptual logic of information and then interpret the conceptual logic of design as a logic of requirements, by introducing the relation of “sufficientisation”. In the conclusion, I argue that the logic of requirements is exactly what we need in order to make sense of, and buttress, a constructionist approach to knowledge. (shrink)

The use of “levels of abstraction” in philosophical analysis (levelism) has recently come under attack. In this paper, I argue that a refined version of epistemological levelism should be retained as a fundamental method, called the method of levels of abstraction. After a brief introduction, in section “Some Definitions and Preliminary Examples” the nature and applicability of the epistemological method of levels of abstraction is clarified. In section “A Classic Application of the Method ofion”, the philosophical fruitfulness of the new (...) method is shown by using Kant’s classic discussion of the “antinomies of pure reason” as an example. In section “The Philosophy of the Method of Abstraction”, the method is further specified and supported by distinguishing it from three other forms of “levelism”: (i) levels of organisation; (ii) levels of explanation and (iii) conceptual schemes. In that context, the problems of relativism and antirealism are also briefly addressed. The conclusion discusses some of the work that lies ahead, two potential limitations of the method and some results that have already been obtained by applying the method to some long-standing philosophical problems. (shrink)

The article addresses the problem of how semantic information can be upgraded to knowledge. The introductory section explains the technical terminology and the relevant background. Section 2 argues that, for semantic information to be upgraded to knowledge, it is necessary and sufficient to be embedded in a network of questions and answers that correctly accounts for it. Section 3 shows that an information flow network of type A fulfils such a requirement, by warranting that the erotetic deficit, characterising the target (...) semantic information t by default, is correctly satisfied by the information flow of correct answers provided by an informational source s. Section 4 illustrates some of the major advantages of such a Network Theory of Account (NTA) and clears the ground of a few potential difficulties. Section 5 clarifies why NTA and an informational analysis of knowledge, according to which knowledge is accounted semantic information, is not subject to Gettier-type counterexamples. A concluding section briefly summarises the results obtained. (shrink)

The tripartite account of propositional, fallibilist knowledge that p as justified true belief can become adequate only if it can solve the Gettier Problem. However, the latter can be solved only if the problem of a successful coordination of the resources (at least truth and justification) necessary and sufficient to deliver propositional, fallibilist knowledge that p can be solved. In this paper, the coordination problem is proved to be insolvable by showing that it is equivalent to the ''''coordinated attack'''' problem, (...) which is demonstrably insolvable in epistemic logic. It follows that the tripartite account is not merely inadequate as it stands, as proved by Gettier-type counterexamples, but demonstrably irreparable in principle, so that efforts to improve it can never succeed. (shrink)

This article reports the findings of AI4People, an Atomium—EISMD initiative designed to lay the foundations for a “Good AI Society”. We introduce the core opportunities and risks of AI for society; present a synthesis of five ethical principles that should undergird its development and adoption; and offer 20 concrete recommendations—to assess, to develop, to incentivise, and to support good AI—which in some cases may be undertaken directly by national or supranational policy makers, while in others may be led by other (...) stakeholders. If adopted, these recommendations would serve as a firm foundation for the establishment of a Good AI Society. (shrink)

We compare Karl Popper’s ideas concerning the falsifiability of a theory with similar notions from the part of statistical learning theory known as VC-theory . Popper’s notion of the dimension of a theory is contrasted with the apparently very similar VC-dimension. Having located some divergences, we discuss how best to view Popper’s work from the perspective of statistical learning theory, either as a precursor or as aiming to capture a different learning activity.

In their rich and intricate paper ‘Independence, Invariance, and the Causal Markov Condition’, Daniel Hausman and James Woodward ([1999]) put forward two independent theses, which they label ‘level invariance’ and ‘manipulability’, and they claim that, given a specific set of assumptions, manipulability implies the causal Markov condition. These claims are interesting and important, and this paper is devoted to commenting on them. With respect to level invariance, I argue that Hausman and Woodward's discussion is confusing because, as I point out, (...) they use different senses of ‘intervention’ and ‘invariance’ without saying so. I shall remark on these various uses and point out that the thesis is true in at least two versions. The second thesis, however, is not true. I argue that in their formulation, the manipulability thesis is patently false and that a modified version does not fare better. Furthermore, I think their proof that manipulability implies the causal Markov condition is not conclusive. In the deterministic case it is valid but vacuous, whereas it is invalid in the probabilistic case. 1 Introduction 2 Intervention, invariance and modularity 3 The causal Markov condition: CM1 and CM2 4 From MOD to the causal Markov condition and back 5 A second argument for CM2 6 The proof of the causal Markov condition for probabilistic causes 7 ‘Cartwright's objection’ defended 8 Metaphysical defenses of the causal Markov condition 9 Conclusion. (shrink)

The aim of this book is to discuss the fundamental ideas which lie behind the statistical theory of learning and generalization. It considers learning as a general problem of function estimation based on empirical data. Omitting proofs and technical details, the author concentrates on discussing the main results of learning theory and their connections to fundamental problems in statistics. This second edition contains three new chapters devoted to further development of the learning theory and SVM techniques. Written in a readable (...) and concise style, the book is intended for statisticians, mathematicians, physicists, and computer scientists. (shrink)

Causality offers the first comprehensive coverage of causal analysis in many sciences, including recent advances using graphical methods. Pearl presents a unified account of the probabilistic, manipulative, counterfactual and structural approaches to causation, and devises simple mathematical tools for analyzing the relationships between causal connections, statistical associations, actions and observations. The book will open the way for including causal analysis in the standard curriculum of statistics, artificial intelligence, business, epidemiology, social science and economics.

In _Reliable Reasoning_, Gilbert Harman and Sanjeev Kulkarni -- a philosopher and an engineer -- argue that philosophy and cognitive science can benefit from statistical learning theory, the theory that lies behind recent advances in machine learning. The philosophical problem of induction, for example, is in part about the reliability of inductive reasoning, where the reliability of a method is measured by its statistically expected percentage of errors -- a central topic in SLT. After discussing philosophical attempts to evade the (...) problem of induction, Harman and Kulkarni provide an admirably clear account of the basic framework of SLT and its implications for inductive reasoning. They explain the Vapnik-Chervonenkis dimension of a set of hypotheses and distinguish two kinds of inductive reasoning. The authors discuss various topics in machine learning, including nearest-neighbor methods, neural networks, and support vector machines. Finally, they describe transductive reasoning and suggest possible new models of human reasoning suggested by developments in SLT. (shrink)

The chapters in this book highlight the multifaceted nature of the process of scientific research.

Approaches to explanation -- Causal and explanatory relevance -- The kairetic account of /D making -- The kairetic account of explanation -- Extending the kairetic account -- Event explanation and causal claims -- Regularity explanation -- Abstraction in regularity explanation -- Approaches to probabilistic explanation -- Kairetic explanation of frequencies -- Kairetic explanation of single outcomes -- Looking outward -- Looking inward.

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that "All models are wrong but some are useful." We focus on (...) the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly. (shrink)

This paper explores some issues concerning the nature and structure of causal explanation in psychiatry and psychology from the point of view of the “interventionist” theory defended in my book, Making Things Happen. Among the issues is explored is the extent to which candidate causal explanations involving “upper level” or relatively coarse-grained or macroscopic variables such as mental/psychological states (e.g. highly self critical beliefs or low self esteem) or environmental factors (e.g. parental abuse) compete with explanations that instead appeal to (...) underlying, “lower level” or more fine gained neural, genetic, or biochemical mechanisms. (shrink)