Machine learning algorithms may radically improve our ability to diagnose and treat disease. For moral, legal, and scientific reasons, it is essential that doctors and patients be able to understand and explain the predictions of these models. Scalable, customisable, and ethical solutions can be achieved by working together with relevant stakeholders, including patients, data scientists, and policy makers.

DCPS is a connectionist production system interpreter that uses distributed representations. As a connectionist model it consists of many simple, richly interconnected neuron‐like computing units that cooperate to solve problems in parallel. One motivation for constructing DCPS was to demonstrate that connectionist models are capable of representing and using explicit rules. A second motivation was to show how “coarse coding” or “distributed representations” can be used to construct a working memory that requires far fewer units than the number of different (...) facts that can potentially be stored. The simulation we present is intended as a detailed demonstration of the feasibility of certain ideas and should not be viewed as a full implementation of production systems. Our current model only has a few of the many interesting emergent properties that we eventually hope to demonstrate: It is damage‐resistant, it performs matching and variable binding by massively parallel constraint satisfaction, and the capacity of its working memory is dependent on the similarity of the items being stored. (shrink)

We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealised explanation game in which players collaborate to find the best explanation for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal (...) patterns of variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealisedexplanation gamein which players collaborate to find the best explanation(s) for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal patterns of (...) variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a (conditionally) optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

_Real Essentialism_ presents a comprehensive defence of neo-Aristotelian essentialism. Do objects have essences? Must they be the kinds of things they are in spite of the changes they undergo? Can we know what things are really like – can we define and classify reality? Many, if not most, philosophers doubt this, influenced by centuries of empiricism, and by the anti-essentialism of Wittgenstein, Quine, Popper, and other thinkers. _Real Essentialism_ reinvigorates the tradition of realist, essentialist metaphysics, defending the reality and knowability (...) of essence, the possibility of objective, immutable definition, and its relevance to contemporary scientific and metaphysical issues such as whether essence transcends physics and chemistry, the essence of life, the nature of biological species, and the nature of the person. (shrink)

As machine learning has gradually entered into ever more sectors of public and private life, there has been a growing demand for algorithmic explainability. How can we make the predictions of complex statistical models more intelligible to end users? A subdiscipline of computer science known as interpretable machine learning (IML) has emerged to address this urgent question. Numerous influential methods have been proposed, from local linear approximations to rule lists and counterfactuals. In this article, I highlight three conceptual challenges that (...) are largely overlooked by authors in this area. I argue that the vast majority of IML algorithms are plagued by (1) ambiguity with respect to their true target; (2) a disregard for error rates and severe testing; and (3) an emphasis on product over process. Each point is developed at length, drawing on relevant debates in epistemology and philosophy of science. Examples and counterexamples from IML are considered, demonstrating how failure to acknowledge these problems can result in counterintuitive and potentially misleading explanations. Without greater care for the conceptual foundations of IML, future work in this area is doomed to repeat the same mistakes. (shrink)

We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealised explanation game in which players collaborate to find the best explanation for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal (...) patterns of variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

"Nivison brings out the exciting variety within Confucian thought, as he interprets and elucidates key thinkers from over two thousand years, from Confucius himself, through Mencius and Xunzi, to such later Confucians as Wang Yangming, Dai Zhen, and Zhang Xuecheng."--Cover.

We examine two different descriptions of the behavioral functions of the hippocampal system. One emphasizes spatially organized behaviors, especially those using cognitive maps. The other emphasizes memory, particularly working memory, a short-term memory that requires iexible stimulus-response associations and is highly susceptible to interference. The predictive value of the spatial and memory descriptions were evaluated by testing rats with damage to the hippocampal system in a series of experiments, independently manipulating the spatial and memory characteristics of a behavioral task. No (...) dissociations were found when the spatial characteristics of the stimuli to be remembered were changed; lesions produced a similar deficit in both spatial and nonspatial test procedures, indicating that the hippocampus was similarly involved regardless of the spatial nature of the task. In contrast, a marked dissociation was found when the memory requirements were altered. Rats with lesions were able to perform accurately in tasks that could be solved exclusively on the basis of reference memory. They performed at chance levels and showed no signs of recovery even with extensive postoperative training in tasks that required working memory. In one experiment all the characteristics of the reference memory and working memory procedures were identical except the type of memory required. Consequently, the behavioral dissociation cannot be explained by differences in attention, motivation, response inhibition, or the type of stimuli to be remembered. As a result of these experiments we propose that the hippocampus is selectively involved in behaviors that require working memory, irrespective of the type of material that is to be processed by that memory. (shrink)

Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence, a fast-growing research area that is so far lacking in firm theoretical foundations. In this article, an expanded version of a paper originally presented at the 37th Conference on Uncertainty in Artificial Intelligence, we attempt to fill this gap. Building on work in logic, probability, and causality, we establish the central role of (...) necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We propose a novel formulation of these concepts, and demonstrate its advantages over leading alternatives. We present a sound and complete algorithm for computing explanatory factors with respect to a given context and set of agentive preferences, allowing users to identify necessary and sufficient conditions for desired outcomes at minimal cost. Experiments on real and simulated data confirm our method’s competitive performance against state of the art XAI tools on a diverse array of tasks. (shrink)

Unsupervised learning algorithms are widely used for many important statistical tasks with numerous applications in science and industry. Yet despite their prevalence, they have attracted remarkably little philosophical scrutiny to date. This stands in stark contrast to supervised and reinforcement learning algorithms, which have been widely studied and critically evaluated, often with an emphasis on ethical concerns. In this article, I analyze three canonical unsupervised learning problems: clustering, abstraction, and generative modeling. I argue that these methods raise unique epistemological and (...) ontological questions, providing data-driven tools for discovering natural kinds and distinguishing essence from contingency. This analysis goes some way toward filling the lacuna in contemporary philosophical discourse on unsupervised learning, as well as bringing conceptual unity to a heterogeneous field more often described by what it isnot(i.e., supervised or reinforcement learning) than by what itis. I submit that unsupervised learning is not just a legitimate subject of philosophical inquiry but perhaps the most fundamental branch of all AI. However, an uncritical overreliance on unsupervised methods poses major epistemic and ethical risks. I conclude by advocating for a pragmatic, error-statistical approach that embraces the opportunities and mitigates the challenges posed by this powerful class of algorithms. (shrink)

The distinction between the essence of an object and its properties has been obscured in contemporary discussion of essentialism. Locke held that the properties of an object are exclusively those features that ‘flow’ from its essence. Here he follows the Aristotelian theory, leaving aside Locke’s own scepticism about the knowability of essence. I defend the need to distinguish sharply between essence and properties, arguing that essence must be given by form and that properties flow from form. I give a precise (...) definition of what the term of art ‘flow’ amounts to, and apply the distinction to various kinds of taxonomic issues. (shrink)

The combination of ethnographic and cognitive neuroscience research provides considerable insight into the origin and symbolism of Native Californian rock art. Although made by different social groups for different purposes in various parts of the state, the ethnographic record demonstrates that the art depicts the mental imagery and somatic hallucinations of trance, taken to represent supernatural experiences. When this art is viewed from a cognitive neuroscience perspective, it suggests that the shamanistic state of consciousness was far from primarily "ecstatic," instead (...) often involving the generation of unpleasant emotions; and that biochemical changes during trance necessitated the making of rock art if the memory of these supernatural experiences was to be preserved. (shrink)

To the extent that dualism is even taken to be a serious option in contemporary discussions of personal identity and the philosophy of mind, it is almost exclusively either Cartesian dualism or property dualism that is considered. The more traditional dualism defended by Aristotelians and Thomists, what I call hylemorphic dualism, has only received scattered attention. In this essay I set out the main lines of the hylemorphic dualist position, with particular reference to personal identity. First I argue that overemphasis (...) of the problem of consciousness has had an unhealthy effect on recent debate, claiming instead that we should emphasize the concept of form. Then I bring in the concept of identity by means of the notion of substantial form. I continue by analyzing the relation between form and matter, defending the traditional theses of prime matter and of the unicity of substantial form. I then argue for the immateriality of the substantial form of the human person, viz. the soul, from an account of the human intellect. From this follows the soul's essential independence of matter. Finally, although the soul is the immaterial bearer of personal identity, that identity is still the identity of an essentially embodied being. I explain how these ideas are to be reconciled. Footnotesa I am grateful to Stephen Braude, John Cottingham, John Haldane, David Jehle, Joel Katzav, Eduardo Ortiz, and Fred Sommers for helpful comments and discussion of a draft of this essay. I would also like to thank Ellen Paul, whose suggestions have helped greatly to improve the essay's style and content. (shrink)

This paper describes differences in two perspectives on the idea of virtue as a theoretical foundation for positive organizational ethics (POE). The virtue ethics perspective is grounded in the philosophical tradition, has classical roots, and focuses attention on virtue as a property of character. The positive social science perspective is a recent movement (e.g., positive psychology and positive organizational scholarship) that has implications for POE. The positive social science movement operationalizes virtue through an empirical lens that emphasizes virtuous behaviors. From (...) a virtue ethics perspective, a behaviorally based account of virtue is a weak theory of virtue. Observations are suggested for integrating the two perspectives. First, virtue should always be understood as an excellence and is often an optimal point between extreme dysfunctions on continuum of potential states. Second, an empirical exploration of virtue needs to account for character and context. Finally, the properties of organization-level virtue need to be further specified and explored. Implications and directions for future research are discussed. (shrink)

Political advertising has long been a target for criticism regarding unethical behaviour. This study looks at the attitudes of Australian advertising agency executives and politicians towards ethical issues relating to political advertising. A sample of 101 advertising agency executives and 46 federal politicians were compared and some attitudinal differences were found, which could be areas of tension in the agency-client relationship.

The first English-language collection devoted to Hegel’s Philosophy of Subjective Spirit.

_The first English-language collection devoted to Hegel’s_ Philosophy of Subjective Spirit.

This paper tests the following hypothesis: that the prime matter of classical Aristotelian-Scholastic metaphysics is numerically identical to energy. Is P=E? After outlining the classical Aristotelian concept of prime matter, I provide the master argument for it based on the phenomenon of substantial change. I then outline what we know about energy as a scientific concept, including its role and application in some key fields. Next, I consider the arguments in favour of prime matter being identical to energy, followed by (...) the arguments against. The method used is that of ontological profile comparison: does the profile of prime matter match, in key features, that of energy? An affirmative answer, that P=E, would be a momentous discovery: it would show that one of the most neglected and derided ideas of pre-modern metaphysics – a contributor to its downfall in the wake of the Scientific Revolution – was right all along. From a negative answer we would still learn much about the interaction of science and metaphysics. It turns out, however, given what we currently know, that the answer is not quite as simple as one might hope. (shrink)

Proponents of physical intentionality argue that the classic hallmarks of intentionality highlighted by Brentano are also found in purely physical powers. Critics worry that this idea is metaphysically obscure at best, and at worst leads to panpsychism or animism. I examine the debate in detail, finding both confusion and illumination in the physical intentionalist thesis. Analysing a number of the canonical features of intentionality, I show that they all point to one overarching phenomenon of which both the mental and the (...) physical are kinds, namely finality. This is the finality of ‘final causes’, the long-discarded idea of universal action for an end to which recent proponents of physical intentionality are in fact pointing whether or not they realise it. I explain finality in terms of the concept of specific indifference, arguing that in the case of the mental, specific indifference is realised by the process of abstraction, which has no correlate in the case of physical powers. This analysis, I conclude, reveals both the strength and weakness of rational creatures such as us, as well as demystifying the way in which powers work. (shrink)

Applied Ethics focuses the central concepts of traditional morality from the companion book Moral Theory - rights, justice, the good, virtue, and the fundamental value of human life - on a number of pressing contemporary problems, including abortion, euthanasia, animals, capital punishment, and war.

The Dead Donor Rule holds that removing organs from a living human being without their consent is wrongful killing. The rule still prevails in most countries, and I assume it without argument in order to pose the question: is it possible to have a metaphysically correct, clinically relevant analysis of human death that makes organ donation possible? I argue that the two dominant criteria of death, brain death and circulatory death, are both empirically and metaphysically inadequate as definitions of human (...) death, and therefore of no epistemic value in themselves. I first set out a neo-Aristotelian theory of death as separation of soul (understood as organising principle) and body, which is then fleshed out as loss of organismic integrity. The brain and circulatory criteria are shown to have severe weaknesses as physiological manifestations of loss of integrity. Given the mismatch between what death is metaphysically speaking, and the dominant criteria accepted by clinicians and philosophers, it turns out that only actual bodily decomposition is a sure sign of death. In this I differ from Alan Shewmon, whose important work I discuss in detail. (shrink)

The success of movies like The Artist and Hugo recreated the wonder and magic of silent film for modern audiences, many of whom might never have experienced a movie without sound. But while the American silent movie was one of the most significant popular art forms of the modern age, it is also one that is largely lost to us, as more than eighty percent of silent films have disappeared, the victims of age, disaster, and neglect. We now know about (...) many of these cinematic masterpieces only from the collections of still portraits and production photographs that were originally created for publicity and reference. Capturing the beauty, horror, and moodiness of silent motion pictures, these images are remarkable pieces of art in their own right. In the first history of still camera work generated by the American silent motion picture industry, David S. Shields chronicles the evolution of silent film aesthetics, glamour, and publicity, and provides unparalleled insight into this influential body of popular imagery. Exploring the work of over sixty camera artists, Still recovers the stories of the photographers who descended on early Hollywood and the stars and starlets who sat for them between 1908 and 1928. Focusing on the most culturally influential types of photographs—the performer portrait and the scene still—Shields follows photographers such as Albert Witzel and W. F. Seely as they devised the poses that newspapers and magazines would bring to Americans, who mimicked the sultry stares and dangerous glances of silent stars. He uncovers scene shots of unprecedented splendor—visions that would ignite the popular imagination. And he details how still photographs changed the film industry, whose growing preoccupation with artistry in imagery caused directors and stars to hire celebrated stage photographers and transformed cameramen into bankable names. Reproducing over one hundred and fifty of these gorgeous black-and-white photographs, Still brings to life an entire long-lost visual culture that a century later still has the power to enchant. (shrink)

The question whether two things can be in the same place at the same time is an ambiguous one. At least three distinct questions could be meant: Can two things simpliciter be in the same place at the same time? Can two things of the same kind be in the same place at the same time? Can two substances of the same kind be in the same place at the same time? The answers to these questions vary. In what follows, (...) all three will be discussed in the light both of recent and of classic earlier examinations of the matter. The following theses will be defended. (shrink)

This collection of essays by leading sinologists, historians, and philosophers both challenges and extends the work of David Nivison, whose contributions range across moral philosophy, religious thought, intellectual history, and Chinese language. Nivison himself replies to each essay.

In this paper we examine a puzzle recently posed by Aaron Preston for the traditional realist assay of property (quality) instances. Consider Socrates (a red round spot) and red1—Socrates’ redness. For the traditional realist, both of these entities are concrete particulars. Further, both involve redness being `tied to’ the same bare individuator. But then it appears that red1 is duplicated in its ‘thicker’ particular (Socrates), so that it can’t be predicated of Socrates without redundancy. According to Preston, this suggests that (...) a concrete particular and its property instances aren’t genuinely related. We argue that Preston’s proffered solution here—to treat property instances as “mental constructs”—is fraught with difficulty. We then go on to show how, by fine-tuning the nature of bare particulars, treating them as abstract modes of things rather than concrete particulars, the traditional realist can neatly evade Preston’s puzzle. (shrink)

Virtuousness refers to the pursuit of the highest aspirations in the human condition. It is characterized by human impact, moral goodness, and unconditional societal betterment. Several writers have recently argued that corporations, in addition to being concerned with ethics, should also emphasize an ethos of virtuousness in corporate action. Virtuousness emphasizes actions that go beyond the “do no harm” assumption embedded in most ethical codes of conduct. Instead, it emphasizes the highest and best of the human condition. This research empirically (...) examines the buffering and amplifying effects of virtuousness in organizations. The study hypothesizes that virtuousness has a positive effect on organizations because amplifying dynamics make subsequent virtuous action more likely, and buffering dynamics reduce the harmful effects of downsizing. The study reveals that two types of virtuousness – tonic and phasic – are associated with these effects. (shrink)

Whereas Mereological Essentialism is the thesis that the parts of an object are essential to it, Reverse Mereological Essentialism is the thesis that the whole is essential to its parts. Specifically – since RME is an Aristotelian doctrine – it is a claim not about objects in general but about substances. Here I set out and explain RME as it should be understood from the perspective of the Aristotelian-Scholastic tradition, as well as proposing a kind of master argument for believing (...) it. A number of objections (many of which have been raised by Kathrin Koslicki or Robert Koons) are then considered, the replies to which help further to clarify and motivate RME. The final section considers some important questions concerning parts and matter in light of Ross Inman’s recent defence of RME under the guise of what he calls Substantial Priority. Considering these questions further illustrates right and wrong ways of understanding RME. Overall, the case for RME is strong albeit with a number of difficulties that need to be resolved through further investigation. (shrink)

The old scholastic principle of the "convertibility" of being and goodness strikes nearly all moderns as either barely comprehensible or plain false. "Convertible" is a term of art meaning "interchangeable" in respect of predication, where the predicates can be exchanged salva veritate albeit not salva sensu: their referents are, as the maxim goes, really the same albeit conceptually different. The principle seems, at first blush, absurd. Did the scholastics literally mean that every being is good? Is that supposed to include (...) a cancer, a malaria parasite, an earthquake that kills millions? If every being is good, then no being is bad—but how can that be? To the contemporary philosophical mind, such bafflement is understandable. It derives from the systematic dismantling of the great scholastic edifice that took place over half a millennium. With the loss of the basic concepts out of which that edifice was built, the space created by those concepts faded out of existence as well. The convertibility principle, like virtually all the other scholastic principles (not all, since some do survive and thrive in analytic philosophy), could not persist in a post-scholastic space wholly alien to it. (shrink)

Corruptionism is the view that following physical death, the human being ceases to exist but their soul persists in the afterlife. Survivalism holds that both the human being and their soul persist in the afterlife, as distinct entities, with the soul constituting the human. Each position has its defenders, most of whom appeal both to metaphysical considerations and to the authority of St Thomas Aquinas. Corruptionists claim that survivalism violates a basic principle of any plausible mereology, while survivalists tend to (...) reject the principle, though without as much detail as one would like. In this paper I examine both the key exegetical issues and the mereological question, arguing that Aquinas cannot be shown to have supported the principle in question, and that the principle should be rejected on independent grounds. If correct, some key planks in support of survivalism are established, with others to await further examination. (shrink)