We introduce and discuss a knowledge-driven distillation approach to explaining black-box models by means of two kinds of interpretable models. The first is perceptron (or threshold) connectives, which enrich knowledge representation languages such as Description Logics with linear operators that serve as a bridge between statistical learning and logical reasoning. The second is Trepan Reloaded, an ap- proach that builds post-hoc explanations of black-box classifiers in the form of decision trees enhanced by domain knowledge. Our aim (...) is, firstly, to target a model-agnostic distillation approach exemplified with these two frameworks, secondly, to study how these two frameworks interact on a theoretical level, and, thirdly, to investigate use-cases in ML and AI in a comparative manner. Specifically, we envision that user-studies will help determine human understandability of explanations generated using these two frameworks. (shrink)

Computational systems biologists create and manipulate computational models of biological systems, but they do not always have straightforward epistemic access to the content and behavioural profile of such models because of their length, coding idiosyncrasies, and formal complexity. This creates difficulties both for modellers in their research groups and for their bioscience collaborators who rely on these models. In this paper we introduce a new kind of visualization that was developed to address just this sort of epistemic (...) opacity. The visualization is unusual in that it depicts the dynamics and structure of a computer model instead of that model’s target system, and because it is generated algorithmically. Using considerations from epistemology and aesthetics, we explore how this new kind of visualization increases scientific understanding of the content and function of computer models in systems biology to reduce epistemic opacity. (shrink)

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.

Simple idealized models seem to provide more understanding than opaque, complex, and hyper-realistic models. However, an increasing number of scientists are going in the opposite direction by utilizing opaque machine learning models to make predictions and draw inferences, suggesting that scientists are opting for models that have less potential for understanding. Are scientists trading understanding for some other epistemic or pragmatic good when they choose a machine learning model? Or are the assumptions behind why minimal (...) class='Hi'>models provide understanding misguided? In this paper, using the case of deep neural networks, I argue that it is not the complexity or black box nature of a model that limits how much understanding the model provides. Instead, it is a lack of scientific and empirical evidence supporting the link that connects a model to the target phenomenon that primarily prohibits understanding. (shrink)

Scholarly processes play a pivotal role in discovering, challenging, improving, advancing, synthesizing, codifying, and disseminating knowledge. Since the 17th Century, both the quality and quantity of knowledge that scholarship has produced has increased tremendously, granting academic research a pivotal role in ensuring material and social progress. Artificial Intelligence (AI) is poised to enable a new leap in the creation of scholarly content. New forms of engagement with AI systems, such as collaborations with large language models like GPT-3, offer affordances (...) that will change the nature of both the scholarly process and the artifacts it produces. (shrink)

Concerns over epistemic opacity abound in contemporary debates on Artificial Intelligence (AI). However, it is not always clear to what extent these concerns refer to the same set of problems. We can observe, first, that the terms 'transparency' and 'opacity' are used either in reference to the computational elements of an AI model or to the models to which they pertain. Second, opacity and transparency might either be understood to refer to the properties of AI systems or to the (...) epistemic situation of human agents with respect to these systems. While these diagnoses are independently discussed in the literature, juxtaposing them and exploring possible interrelations will help to get a view of the relevant distinctions between conceptions of opacity and their empirical bearing. In pursuit of this aim, two pertinent conditions affecting computer models in general and contemporary AI in particular are outlined and discussed: opacity as a problem of computational tractability and opacity as a problem of the universality of the computational method. (shrink)

A gas in a box is perhaps the most important model system studied in thermodynamics and statistical mechanics. Usually, studies focus on the gas, whereas the box merely serves as an idealized confinement. The present article focuses on the box as the central object and develops a thermodynamic theory by treating the geometric degrees of freedom of the box as the degrees of freedom of a thermodynamic system. Applying standard mathematical methods to the thermody- namics of an empty box allows (...) equations with the same structure as those of cosmology and classical and quantum mechanics to be derived. The simple model system of an empty box is shown to have interesting connections to classical mechanics, special relativity, and quantum field theory. (shrink)

Without doctors being able to explain medical decisions to patients, I argue their use of black box AIs would erode the effective and respectful care they provide patients. In addition, I argue that physicians should use AI black boxes only for patients in dire straits, or when physicians use AI as a “co-pilot” (analogous to a spellchecker) but can independently confirm its accuracy. I respond to A.J. London’s objection that physicians already prescribe some drugs without knowing why they (...) work. (shrink)

The ‘black box’ in Stoic axiology refers to the mysterious connection between the input of Stoic deliberation (reasons generated by the value of indifferents) and the output (appropriate actions). In this paper, I peer into the black box by drawing an analogy between Stoic and Kantian axiology. The value and disvalue of indifferents is intrinsic, but conditional. An extrinsic condition on the value of a token indifferent is that one's selection of that indifferent is sanctioned by context-relative ethical (...) principles. The value of an indifferent that does not meet this condition is normatively silenced, such that it fails to constitute a reason for action. (shrink)

The model of consciousness developed here is a cooperative venture between mind, brain, body, nature, culture, community, and family. The overall unity of consciousness is provided by the loop of engagement that conducts intentional action into the ambient. Each successive round of engagement between subject and world generates a gap of disparity between remembrance of purpose or intent and the effect achieved on the operative level of understanding within a larger taxonomic scheme in experience. That gap sends a delta signal (...) that arouses various parameters of motivation to form a configuration that constitutes a felt situation within subjective experience. That delta signal and felt situation are nothing other than our subjective experience of consciousness. Situated intelligence is the first-person awareness stimulated by a particular complement of motivational parameters. (shrink)

Fears of black-box algorithms are multiplying. Black-box algorithms are said to prevent accountability, make it harder to detect bias and so on. Some fears concern the epistemology of black-box algorithms in medicine and the ethical implications of that epistemology. In ‘Who is afraid of black box algorithms? On the epistemological and ethical basis of trust in medical AI,' Durán and Jongsma seek to allay such fears. While some of their arguments are compelling, we still see reasons (...) for fear. (shrink)

My aim in this article is to contribute to the larger project of assessing the relative merits of different theories of substance. An important preliminary step in this project is assessing the explanatory resources of one main theory of substance, the so-called bundle theory. This article works towards such an assessment. I identify and explain three distinct explanatory challenges an adequate bundle theory must meet. Each points to a putative explanatory gap, so I call them the Gap Challenges. I consider (...) three bundle-theoretic strategies for meeting these challenges. I argue that none of them goes very far. The upshot is that, absent other strategies for meeting the challenges, bundle theory involves a significant amount of stipulation. This black box makes bundle theory relatively weak with respect to its explanatory power—unless, of course, rival theories of substance are unable to do better. (shrink)

Explainable AI (xAI) methods are important for establishing trust in using black-box models. However, recent criticism has mounted against current xAI methods that they disagree, are necessarily false, and can be manipulated, which has started to undermine the deployment of black-box models. Rudin (2019) goes so far as to say that we should stop using black-box models altogether in high-stakes cases because xAI explanations ‘must be wrong’. However, strict fidelity to the truth is historically (...) not a desideratum in science. Idealizations – the intentional distortions introduced to scientific theories and models – are commonplace in the natural sciences and are seen as a successful scientific tool. Thus, it is not falsehood qua falsehood that is the issue. In this paper, I outline the need for xAI research to engage in idealization evaluation. Drawing on the use of idealizations in the natural sciences and philosophy of science, I introduce a novel framework for evaluating whether xAI methods engage in successful idealizations or deceptive explanations (SIDEs). SIDEs evaluates whether the limitations of xAI methods, and the distortions that they introduce, can be part of a successful idealization or are indeed deceptive distortions as critics suggest. I discuss the role that existing research can play in idealization evaluation and where innovation is necessary. Through a qualitative analysis we find that leading feature importance methods and counterfactual explanations are subject to idealization failure and suggest remedies for ameliorating idealization failure. (shrink)

A ‘Black Box’ cannot be opened to reveal its mechanism. Rather, its operations are inferred through input from (and output to) an ‘observer’. All of us are observers, who attempt to understand the Black Boxes that are Minds. The Black Box and its observer constitute a system, differing from either component alone: a ‘greater’ Black Box to any further-external-observer. To Glanville (1982), the further-external-observer probes the greater-Black-Box by interacting directly with its core Black Box, (...) ignoring that Box’s immediate observer. In later accounts, however, Glanville’s greater-Black-Box inexplicably becomes unitary. Why the discrepancy? To resolve it, we start with von Foerster’s archetype ‘machines’, that are of two kinds: ‘Trivial’ (predictable) and ‘Non-Trivial’ (non-predictable). Early-on, Glanville treated the core Black Box and its observer as Trivial Machines, that gradually ‘whiten’ (reveal) each other though input and output, becoming ‘white boxes’. Later, however, Black Box and observer became Non-Trivial Machines, never fully ‘whitenable’. But Non-Trivial Machines can be concatenated from Trivial Machines, and are the only true Black Boxes; any greater-Black-Box (Non-Trivial Machine) may (within its core Black Box) involve white boxes (that are Trivial Machines). White boxes, therefore, could be the ultimate source of the greatest Black Box of all: the Mind. (shrink)

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts (...) from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders. (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 chapter explores the idea that causal inference is warranted if and only if the mechanism underlying the inferred causal association is identified. This mechanistic stance is discernible in the epidemiological literature, and in the strategies adopted by epidemiologists seeking to establish causal hypotheses. But the exact opposite methodology is also discernible, the black box stance, which asserts that epidemiologists can and should make causal inferences on the basis of their evidence, without worrying about the mechanisms that might underlie (...) their hypotheses. I argue that the mechanistic stance is indeed a bad methodology for causal inference. However, I detach and defend a mechanistic interpretation of causal generalisations in epidemiology as existence claims about underlying mechanisms. (shrink)

This article argues that actor-network theory, as an alternative to critical theory, has lost its critical impetus when examining commodification in healthcare. The paper claims that the reason for this, is the way in which actor-network theory’s anti-essentialist ontology seems to black box 'intentionality' and ethics of human agency as contingent interests. The purpose of this paper was to open the normative black box of commodification, and compare how Marxism, Habermas and ANT can deal with commodification and ethics (...) in healthcare. Moreover, a new account of 'intentionality' in critical thinking was elaborated. Using Strawson's analysis of 'reactive attitudes and resentment,' the ethical implications of commodification in health care were examined as an assessment of intentions. Synthesizing critical theory with the relational materialism of actor-network theory, this article advances a new approach that seeks to bridge interdisciplinary boundaries, and guide actor-network theory in a critical and humanist direction. Providing new theoretical insights on commodification and 'intentionality' in health care. (shrink)

This paper concerns the Black Box. It is not the engineer’s black box that can be opened to reveal its mechanism, but rather one whose operations are inferred through input from (and output to) a companion observer. We are observers ourselves, and we attempt to understand minds through interactions with their host organisms. To this end, Ranulph Glanville followed W. Ross Ashby in elaborating the Black Box. The Black Box and its observer together form a system (...) having different properties than either component alone, making it a greater Black Box to any further-external observer. How far into this greater box can a further-external observer probe? The answer is crucial to understanding Black Boxes, and so an answer is offered here. It employs von Foerster’s machines, abstract entities having mechano-electrical bases, just like putative Black Boxes. Von Foerster follows Turing, Ashby, E. F. Moore, and G. H. Mealy in recognizing archetype machines that he calls trivial (predictable) and non-trivial (non-predictable). It is argued here that non-trivial machines are the only true Black Boxes. But non-trivial machines can be concatenated from trivial machines. Hence, the utter core of any greater Black Box (a non-trivial machine) may involve two (or more) White Boxes (trivial machines). This is how an unpredictable thing emerges from predictable parts. Interactions of White Boxes—of trivial machines—may be the ultimate source of the mind. Keywords: . (shrink)

In the context of the digital economy development, the priority component of the economic security of an enterprise is changing from material to digital, constituting an independent element of enterprise security. The relevance of the present research is driven by the need to solve the issue of modernizing the economic security of the enterprise taking into account the new risks and opportunities of digitalization. The purpose of the academic paper lies in identifying the features of preventing internal and external negative (...) influences (threats) in order to guarantee the effective and stable functioning and dynamic social development of the enterprise in the context of digitalization. The research methods are as follows: general scientific research methods, in particular, logical analysis, theoretical substantiation, methods of induction and deduction, formalization and generalization, statistical observation. Results. It has been proposed to introduce the concept of “digital security of the enterprise” for replacing the concept of “information component of economic security” in order to bring the terminology in line with new economic realities. The implementation of the “black box” model has made it possible to identify the latest risks and threats to the economic security of an enterprise within the conditions of the digitalization that differs from the existing ones. The assessment of enterprises’ digital security of the European Union member states has revealed that the digital security level does not depend on the size of the country, however, it is influenced by the institutional environment (in particular, digital development tools in the EU) and the size of enterprises. Also, within the research framework, an assessment of the digital security level of enterprises in the context of digitalization has been proposed. In order to characterize enterprises by the level of digital security, a calculation procedure using the coefficient method has been proposed. (shrink)

Im Beitrag wird die Apple-Watch vor dem Hintergrund ihrer „Ästhetik der Existenz“ als biopolitisches Artefakt und kontrollgesellschaftliches Dispositiv, vor allem aber als kybernetische Black Box aufgefasst und analysiert. Ziel des Aufsatzes ist es, aufzuzeigen, dass sich in dem feedbacklogischen Rückkopplungsapparat nicht nur grundlegende Diskurse des digitalen Zeitalters (Prävention, Gesundheit, bio- und psychopolitische Regulierungsformen etc.) verdichten, sondern dass dieser schon ob seiner inhärenten Logik qua Opazität Transparenz, qua Komplexität Simplizität (d.h. Orientierung) generiert und damit nicht zuletzt ein ganz spezifisches Menschenbild (...) forciert. In methodischer Hinsicht sollen zur Aufschlüsselung der für die digitale Gesellschaft repräsentativen Black Box „Apple-Watch“ wirksame Begriffskonstellationen der Kybernetik – d.h. Feedback, Regulierung, Selbstkontrolle und nicht zuletzt das Prinzip des „schwarzen Kastens“ selbst (Wiener/ Ashby), in dem sich schon die Funktion des Apparats als (Selbst-)Regulierungstool zwischen In- und Outputs reflektiert – in den Blick genommen und mit behavioristischen Konzepten (besonders solche der Gegenwart, d.h. nudging-Konzepte etc.) kontextualisiert werden. Auf dieser Grundlage lässt sich schließlich, so die These, nicht nur ein Subjektivierungsmodell ableiten, sondern auch eine (durchaus realpolitisch wirksame) Regierungskunst („kybernetische Gouvernementalität“) dekodieren. In diesem Zusammenhang ist schließlich die These zu plausibilisieren, dass das zeitgenössische „Sicherheitsregime“ des ‚new dark age‘ (Bridle) respektive der ‚Black-Box-Society‘ (Pasquale) sich nicht auf „die Unterdrückung von Subjektivität [bezieht], sondern vor allem auf ihre ‚(Selbst)-Produktion‘, […] auf die […] Förderung von Selbsttechnologien, die an Regierungsziele gekoppelt werden können.“ (Lemke) Entsprechend fragt der Aufsatz, welche – auch politischen – Auswirkungen die exzessive Verbreitung dieser und ähnlicher „smart devices“ zeitigt: Denn nicht zuletzt lässt sich, mediiert über derartige datengenerierende schwarze Kästen, eine Form der Regierung und des Regierbar-Machens erkennen, die weniger explizit-imperativisch auf Subjekte als vielmehr implizit-suggestiv auf Datenpunkte und -profile einwirkt. (shrink)

Nonostante la pervasività della nozione di servizio e le recenti proposte per una Scienza dei Servizi unificata, esistono ancora parecchie inconsistenze tra le varie definizioni di servizio in uso nelle diverse discipline (e spesso anche all'interno della stessa disciplina). In particolare, a dispetto del fatto che l'obiettivo generale di questa scienza dovrebbe essere di permettere a persone e calcolatori di interagire agevolmente con i servizi nella vita di tutti i giorni, molti approcci alla modellazione dei servizi in informatica (specialmente quelli (...) centrati sui servizi web) sembrano focalizzarsi principalmente sugli aspetti connessi al flusso dati, per cui i servizi sono considerati come scatole nere che trasformano un ingresso in un’uscita, e che interoperano tra loro secondo modalità predefinite. Questo modello a scatola nera ha sicuramente i suoi vantaggi ma, stando a quanto dicono Petrie e Bussler, sembra funzionare bene sono all'interno di contesti omogenei, i cosiddetti parchi di servizi, dove l'interoperabilità è tecnicamente possibile solo perché i contenuti e le modalità di erogazione di ogni servizio sono predefiniti e condivisi da tutti i soggetti coinvolti. (shrink)

In recent years, the economics of emotions (EoE) field, which aims to create models of the human mind, has grown quickly. EoE models work well with simulation theory (ST), which is one of the main theories of mind. EoE models show how people's behavior and emotions change based on their knowledge and perception of others. It is hoped that by developing this model, it will be possible to quantitatively analyze not only the mental states of real others, (...) but also the subtleties of the minds of characters in novels in the future. Until now, the decision-making or the factual-reasoning mechanisms have been a black box in ST. This study analyzes how EoE models add to the understanding of ST. (shrink)

Darwin provided us with a powerful theoretical framework to explain the evolution of living systems. Natural selection alone, however, has sometimes been seen as insufficient to explain the emergence of new levels of selection. The problem is one of “circularity” for evolutionary explanations: how to explain the origins of Darwinian properties without already invoking their presence at the level they emerge. That is, how does evolution by natural selection commence in the first place? Recent results in experimental evolution suggest a (...) way forward: Paul Rainey and his collaborators have shown that Darwinian properties could be exogenously imposed via what they call “ecological scaffolding.” This could solve the “black box” dilemma faced by Darwinian explanations of new levels of organization. Yet, despite “scaffolding” recently becoming a popular term in the study of cognition, culture, and evolution, the concept has suffered from vagueness and ambiguity. This article aims to show that scaffolding can be turned into a proper scientific concept able to do explanatory work within the context of the major evolutionary transitions. Doing so will allow us to once again extend the scope of the Darwinian model of evolution by natural selection. (shrink)

There are two distinct approaches to Bayesian modelling in cognitive science. Black-box approaches use Bayesian theory to model the relationship between the inputs and outputs of a cognitive system without reference to the mediating causal processes; while mechanistic approaches make claims about the neural mechanisms which generate the outputs from the inputs. This paper concerns the relationship between these two approaches. We argue that the dominant trend in the philosophical literature, which characterizes the relationship between black-box and mechanistic (...) approaches to Bayesian cognitive science in terms of the dichotomy between instrumentalism and realism, is misguided. We propose that the two distinctions are orthogonal: black-box and mechanistic approaches to Bayesian modelling can each be given either an instrumentalist or a realist interpretation. We argue that the current tendency to conflate black-box approaches with instrumentalism and mechanistic approaches with realism stems from unwarranted assumptions about the nature of scientific explanation, the ontological commitments of scientific theories, and the role of abstraction and idealization in scientific models. We challenge each of these assumptions to reframe the debates over Bayesian modelling in cognitive science. (shrink)

One of the primary, if not most critical, difficulties in the design and implementation of autonomous systems is the black-boxed nature of the decision-making structures and logical pathways. How human values are embodied and actualised in situ may ultimately prove to be harmful if not outright recalcitrant. For this reason, the values of stakeholders become of particular significance given the risks posed by opaque structures of intelligent agents (IAs). This paper explores how decision matrix algorithms, via the belief-desire-intention model (...) for autonomous vehicles, can be designed to minimize the risks of opaque architectures. Primarily through an explicit orientation towards designing for the values of explainability and verifiability. In doing so, this research adopts the Value Sensitive Design (VSD) approach as a principled framework for the incorporation of such values within design. VSD is recognized as a potential starting point that offers a systematic way for engineering teams to formally incorporate existing technical solutions within ethical design, while simultaneously remaining pliable to emerging issues and needs. It is concluded that the VSD methodology offers at least a strong enough foundation from which designers can begin to anticipate design needs and formulate salient design flows that can be adapted to the changing ethical landscapes required for utilisation in autonomous vehicles. (shrink)

The use of machine learning algorithms has become ubiquitous in hiring decisions. Recent studies have shown that many of these algorithms generate unlawful discriminatory effects in every step of the process. The training phase of the machine learning models used in these decisions has been identified as the main source of bias. For a long time, discrimination cases have been analyzed under the banner of disparate treatment and disparate impact, but these concepts have been shown to be ineffective in (...) the context of AI. This paper examines the possibility of studying algorithmic discrimination from the perspective of negligence law. Negligent selection and validation of datasets and classifiers is a salient cause of improper training in machine learning. It is a breach of an employer’s duty to protect others, a failure of its exercise of due care in the manner of choosing employees. Adopting negligence to algorithmic discrimination requires a reformulation of what is foreseeable and reasonable within the context of black box algorithms, and a shift in the burden of proof to the employer, who must present evidence of its efforts to avoid bias. (shrink)

The present paper looks at one of the most thorough articles on the intelligence of GPT, research conducted by engineers at Microsoft. Although there is a great deal of value in their work, I will argue that, for familiar philosophical reasons, their methodology, ‘Black-box Interpretability’ is wrongheaded. But there is a better way. There is an exciting and emerging discipline of ‘Inner Interpretability’ (also sometimes called ‘White-box Interpretability’) that aims to uncover the internal activations and weights of models (...) in order to understand what they represent and the algorithms they implement. In my view, a crucial mistake in Black-box Interpretability is the failure to appreciate that how processes are carried out matters when it comes to intelligence and understanding. I can’t pretend to have a full story that provides both necessary and sufficient conditions for being intelligent, but I do think that Inner Interpretability dovetails nicely with plausible philosophical views of what intelligence requires. So the conclusion is modest, but the important point in my view is seeing how to get the research on the right track. Towards the end of the paper, I will show how some of the philosophical concepts can be used to further refine how Inner Interpretability is approached, so the paper helps draw out a profitable, future two-way exchange between Philosophers and Computer Scientists. (shrink)

We call for a new philosophical conception of models in physics. Some standard conceptions take models to be useful approximations to theorems, that are the chief means to test theories. Hence the heuristics of model building is dictated by the requirements and practice of theory-testing. In this paper we argue that a theory-driven view of models can not account for common procedures used by scientists to model phenomena. We illustrate this thesis with a case study: the construction (...) of one of the first comprehensive model of superconductivity by London brothers in 1934. Instead of theory-driven view of models, we suggest a phenomenologically-driven one. (shrink)

The article considers the problem of images and the role they play in our reflection turning to evidence provided by two seemingly very distant theories of mind together with two sorts of corresponding visions: dreams as analyzed by Freud who claimed that they are pictures of our thoughts, and their mechanical counterparts produced by neural networks designed for object recognition and classification. Freud’s theory of dreams has largely been ignored by philosophers interested in cognition, most of whom focused solely on (...) the linguistic incarnation of thoughts, but even though commonly neglected by respectable theories of thinking, dream images may prove to be the key to the black box of thought. As argued in this article, when seen from the right perspective and approached with the right set of questions, oneiric visions yield groundbreaking insights into the mechanism of how concepts and judgments are formed. Support for this conclusion comes from a tradition seemingly remote, if not opposed to psychoanalysis: the mechanical model of the mind conceived by information sciences and embodied in the form of artificial neural nets which mirror the activity of human visual cortex producing visions strikingly similar to those created by the sleeping mind. These purely mechanical, artificial ‘dreams’ constitute byproducts of algorithms designed for object recognition and classification, which, as I shall argue, reveals the true purpose of our own oneiric visual formations. Just like their mechanical counterparts produced by neural networks, condensations and displacements encountered in dreams are in fact visual universals. (shrink)

The opacity of some recent Machine Learning (ML) techniques have raised fundamental questions on their explainability, and created a whole domain dedicated to Explainable Artificial Intelligence (XAI). However, most of the literature has been dedicated to explainability as a scientific problem dealt with typical methods of computer science, from statistics to UX. In this paper, we focus on explainability as a pedagogical problem emerging from the interaction between lay users and complex technological systems. We defend an empirical methodology based on (...) field work, which should go beyond the in-vitro analysis of UX to examine in-vivo problems emerging in the field. Our methodology is also comparative, as it chooses to steer away from the almost exclusive focus on ML to compare its challenges with those faced by more vintage algorithms. Finally, it is also philosophical, as we defend the relevance of the philosophical literature to define the epistemic desiderata of a good explanation. This study was conducted in collaboration with Etalab, a Task Force of the French Prime Minister in charge of Open Data & Open Government Policies, dealing in particular with the enforcement of the right to an explanation. In order to illustrate and refine our methodology before going up to scale, we conduct a preliminary work of case studies on the main different types of algorithms used by the French administration: computation, matching algorithms and ML. We study the merits and drawbacks of a recent approach to explanation, which we baptize input-output black box reasoning or BBR for short. We begin by presenting a conceptual framework including the distinctions necessary to a study of pedagogical explainability. We proceed to algorithmic case studies, and draw model-specific and model-agnostic lessons and conjectures. (shrink)

There has been a push in recent years to provide better explanations for how AIs make their decisions. Most of this push has come from the ethical concerns that go hand in hand with AIs making decisions that affect humans. Outside of the strictly ethical concerns that have prompted the study of explainable AIs (XAIs), there has been research interest in the mere possibility of creating XAIs in various domains. In general, the more accurate we make our models the (...) harder they are to explain. Go playing AIs like AlphaGo and KataGo provide fantastic examples of this phenomenon. In this paper, I discuss a non-exhaustive list of the leading theories of explanation and what each of these theories would say about the explainability of AI-played moves of Go. Finally, I consider the possibility of ever explaining AI-played Go moves in a way that meets the four principles of XAI. I conclude, somewhat pessimistically, that Go is not as imminently explainable as other domains. As such, the probability of having an XAI for Go that meets the four principles is low. (shrink)

With the fast pace of AI development, the problem of preventing its global catastrophic risks arises. However, no satisfactory solution has been found. From several possibilities, the confinement of AI in a box is considered as a low-quality possible solution for AI safety. However, some treacherous AIs can be stopped by effective confinement if it is used as an additional measure. Here, we proposed an idealized model of the best possible confinement by aggregating all known ideas in the field of (...) AI boxing. We model the confinement based on the principles used in the safety engineering of nuclear power plants. We show that AI confinement should be implemented in several levels of defense. These levels include 1) AI design in fail-safe manner 2) limiting its capabilities, preventing self-improving and circuit breakers on treacherous turn 3) isolation from the outside world and, lastly, as the final hope 4) outside measures oriented on stopping AI in the wild. We demonstrate that the substantial number (more than 50 ideas listed in the article) of mutually independent measures could provide a relatively high probability of the containment of a human-level AI but may be not sufficient to preserve runaway of superintelligent AI. Thus, these measures will work only if they are used to prevent superintelligent AI creation, but not for containing superintelligence. We suggest that there could be a safe operation threshold, on which AI is useful, but is not able to hack containment system from the inside, the same way as a safe level of chain reaction inside nuclear power plants is maintained. However, overall, a failure of the confinement is inevitable, so we need to use the full AGI limited number of times (AI-ticks). (shrink)

Macroscopic irreversible processes emerge from fundamental physical laws of reversible character. The source of the local irreversibility seems to be not in the laws themselves but in the initial and boundary conditions of the equations that represent the laws. In this work we propose that the screening of currents by black hole event horizons determines, locally, a preferred direction for the flux of electromagnetic energy. We study the growth of black hole event horizons due to the cosmological expansion (...) and accretion of cosmic microwave background radiation, for different cosmological models. We propose generalized McVittie co-moving metrics and integrate the rate of accretion of cosmic microwave background radiation onto a supermassive black hole over cosmic time. We find that for flat, open, and closed Friedmann cosmological models, the ratio of the total area of the black hole event horizons with respect to the area of a radial co-moving space-like hypersurface always increases. Since accretion of cosmic radiation sets an absolute lower limit to the total matter accreted by black holes, this implies that the causal past and future are not mirror symmetric for any spacetime event. The asymmetry causes a net Poynting flux in the global future direction; the latter is in turn related to the ever increasing thermodynamic entropy. Thus, we expose a connection between four different “time arrows”: cosmological, electromagnetic, gravitational, and thermodynamic. (shrink)

Some physicians, in their care of patients at risk of misusing opioids, use machine learning (ML)-based prediction drug monitoring programmes (PDMPs) to guide their decision making in the prescription of opioids. This can cause a conflict: a PDMP Score can indicate a patient is at a high risk of opioid abuse while a patient expressly reports oppositely. The prescriber is then left to balance the credibility and trust of the patient with the PDMP Score. Pozzi1 argues that a prescriber who (...) downgrades the credibility of a patient’s testimony based on a low PDMP Score is epistemically and morally unjustified and contributes to a form of testimonial injustice. This results in patients being silenced, excluded from decision-making processes and subjected to structural injustices. Additionally, the use of ML systems in medical practices raises concerns about perpetuating existing inequalities, overestimating their capabilities and displacing human authority. However, almost the very same critiques apply to human-based systems. Formalisation, ML systems included, should instead be viewed positively,2 and precisely as a powerful means to begin eroding these and other problems in ethically sensitive domains. In this case, the epistemic virtues of formalisation include promoting transparency, consistency and replicability in decision making. Rigorous ML systems can also help ensure that models …. (shrink)

Public health care interventions—regarding vaccination, obesity, and HIV, for example—standardly take the form of information dissemination across a community. But information networks can vary importantly between different ethnic communities, as can levels of trust in information from different sources. We use data from the Greater Pittsburgh Random Household Health Survey to construct models of information networks for White and Black communities--models which reflect the degree of information contact between individuals, with degrees of trust in information from various (...) sources correlated with positions in that social network. With simple assumptions regarding belief change and social reinforcement, we use those modeled networks to build dynamic agent-based models of how information can be expected to flow and how beliefs can be expected to change across each community. With contrasting information from governmental and religious sources, the results show importantly different dynamic patterns of belief polarization within the two communities. (shrink)

Does intersectionality divide marginalized groups (e.g., women) along identity lines (e.g., race, class, and sexuality)? In response to the criticism that intersectional approaches to feminist and critical race theories lead to fragmentation and division, this paper notes that it relies on an ontological (mis)understanding of identity as a fixed entity. I argue against this notion of identity by engaging in a detailed case study of how Asian American women experience their Asian identity. The case study demonstrates that identity is lived (...) not as a pre-given static object but rather as a fluid and flexible process: what Asian identity means varies according to how this identity is related to the dynamics of power. I propose a tripartite taxonomy of identity-power relationships exhibited in Asian American women’s lives, in which identities are 1) constructed by and 2) used to reproduce power as oppression, as well as 3) used to build power as resistance. In particular, I explore Black and Asian feminist solidarities to show that those at the margins recreate their identities and, in doing so, build positive forms of power such as resistance and solidarity. The criticism that intersectionality leads to fragmentation does not hold, as it is grounded in a flawed notion of identity that fails to consider how identities are actually lived in their changing relationships to power—especially how marginalized groups, such as women of color, build solidarity to resist oppression by recreating their identities, rather than being fragmented into smaller and mutually exclusive subgroups. (shrink)

ABSTRACT This article offers the first step in an ongoing project of revisiting the foundations of latinidad and lo latinoamericano by focusing on the exclusions enacted by the history of these concepts and the cultural and political identity that comes with them. In conversation with Susana Nuccetelli and Omar Rivera, the author focuses on two emblematic authors in the history of Latin American philosophy (Simón Bolívar and José de Vasconcelos) that are usually read as offering a novel, liberatory conception of (...) the Latin American reality/identity, categorically different from European and Anglo-American conceptions. This common reading of some of the foundational texts on Latin American identity, however, conceals not only the active, textual removal of Blackness in the construction of this identity, but also the literal subtraction of Black bodies, lives, and histories from the Latin American nations and communities. Both of these elements are an explicit part of the philosophical programs of Bolívar and Vasconcelos. The article shows how the thought and political practice of these two authors, celebrated in different ways as foundational of what we understand as Latin America today, exemplify the exclusionary historical demarcation of latinidad. (shrink)

Even where an act appears to be responsible, and satisfies all the conditions for responsibility laid down by society, the response to it may be unjust where that appearance is false, and where those conditions are insufficient. This paper argues that those who want to place considerations of responsibility at the centre of distributive and criminal justice ought to take this concern seriously. The common strategy of relying on what Susan Hurley describes as a 'black box of responsibility' has (...) the advantage of not taking responsibility considerations to be irrelevant merely because some specific account of responsibility is mistaken. It can, furthermore, cope perfectly well with an absence of responsibility, even of the global sort implied by hard determinism and other strongly sceptical accounts. Problems for the black box view come in where responsibility is present, but in a form that is curtailed in one significant regard or another. The trick, then, is to open the box of responsibility just enough that its contents can be the basis for judgements of justice. I identify three 'moderately sceptical' forms of compatibilism that cannot ground judgements of justice, and are therefore expunged by the strongest 'grey box' view. (shrink)

Are idioms stored in memory in ways that preserve their surface form or language or are they represented amodally? We examined this question using an inci- dental cued recall paradigm in which two word idiomatic expressions were presented to adult bilinguals proficient in Russian and English. Stimuli included phrases with idiomat- ic equivalents in both languages (e.g. “empty words/пycтыe cлoвa”) or in one language only (English—e.g. “empty suit/пycтoй кocтюм” or Russian—e.g. “empty sound/пycтoй звyк”), or in neither language (e.g. “empty rain/пycтoй (...) дoждь”). If idioms are stored in a language-specific format, then phrases with idiomatic equivalents in both languages would have dual representation, and should therefore be more easily recalled than phrases with idiomatic meaning in only one language. This result was obtained. As such, the findings support the dual-coding theory of memory and are also compatible with models of the bilingual lexicon that include language tags or nodes. (shrink)

Summary Analogue models are actual physical setups used to model something else. They are especially useful when what we wish to investigate is difficult to observe or experiment upon due to size or distance in space or time: for example, if the thing we wish to investigate is too large, too far away, takes place on a time scale that is too long, does not yet exist or has ceased to exist. The range and variety of analogue models (...) is too extensive to attempt a survey. In this article, I describe and discuss several different analogue model experiments, the results of those model experiments, and the basis for constructing them and interpreting their results. Examples of analogue models for surface waves in lakes, for earthquakes and volcanoes in geophysics, and for black holes in general relativity, are described, with a focus on examining the bases for claims that these analogues are appropriate analogues of what they are used to investigate. A table showing three different kinds of bases for reasoning using analogue models is provided. Finally, it is shown how the examples in this article counter three common misconceptions about the use of analogue models in physics. (shrink)

In his work on the open future, Patrick Todd outlines three models of how to deal with future contingents. These models must answer two questions: one metaphysical, about what facts there are in the world; one semantic, about how to deal with sentences involving ‘will.’ Model 1 has a privileged timeline. Model 2 has an actual future timeline but leaves it indeterminate which timeline that is. Model 3 has no future timeline. All three give will-sentences a modal treatement, (...) as a box over available futures. I will argue that Todd’s second model has problems and should be improved. The first is that it denies what Todd labels as the basic metaphysical intuition behind open-futurism. The second is that indeterminacy about the facts that characterize the actual timeline breaks through into indeterminate identity. I propose a fix to model 2 eliminating its actual future and resolving an issue that arises in applying the neutral semantics Todd endorses to indeterminate sentences. This improved model, I suggest, may even compare favorably to Todd’s preferred model 3. (shrink)

“Black Star” music video was released two days before Bowie’s death. It bears various implications of dying and the notion of mortality is both literal and metaphorical. It is highly autobiographical and serves as a theatrical stage for Bowie to act both as a music performer and as a self-conscious human being. In this paper, we discuss the signs of mortality in Bowie’s “Black Star” music video-clip. We focus on video’s cinematic techniques and codes, on its motivic elements (...) and on its narrative in relation with music, lyrics, characters, and gestures. We also discuss the video’s intertextual references and the broader signification of the black star figure. We adopt a quasi-semiotic approach considering “Black Star” music video-clip as a text which can be investigated through its signs, codes, and conventions of the musical, visual, and cinematic languages as well. Our interdisciplinary tools derive from visual semiotics and audiovisual analysis models, without leaving outside Bowie’s musical-artistic and personal history. As it turns out, Bowie created a video clip that is philosophical in nature and poetic in structure, preserving the role of protagonist. With the visuals creating a psychedelic atmosphere, the lyrics often are heard as a personal confession. They both generate cognitive and emotional responses that influence the way the viewers-listeners may experience, decompose, and interpret Bowie’s artistic endeavor bridging life and death. (shrink)

I analyse three most interesting and extensive approaches to theoretical models: classical ones—proposed by Peter Achinstein and Michael Redhead, and the rela-tively rareanalysed approach of Ryszard Wójcicki, belonging to a later phase of his research where he gave up applyingthe conceptual apparatus of logical semantics. I take into consideration the approaches to theoretical models in which they are qualified as models representing the reality. That is why I omit Max Black’s and Mary Hesse’s concepts of such (...) models, as those two concepts belong to the analogue model group if we consider the main function of the model of a given class as its classification criterion. My main focus is on theoretical models with representative functions as these very models and, in a broader context, the question of representation. (shrink)

Advanced AI systems are rapidly making their way into medical research and practice, and, arguably, it is only a matter of time before they will surpass human practitioners in terms of accuracy, reliability, and knowledge. If this is true, practitioners will have a prima facie epistemic and professional obligation to align their medical verdicts with those of advanced AI systems. However, in light of their complexity, these AI systems will often function as black boxes: the details of their contents, (...) calculations, and procedures cannot be meaningfully understood by human practitioners. When AI systems reach this level of complexity, we can also speak of black-box medicine. In this paper, we want to argue that black-box medicine conflicts with core ideals of patient-centered medicine. In particular, we claim, black-box medicine is not conducive for supporting informed decision-making based on shared information, shared deliberation, and shared mind between practitioner and patient. (shrink)

A physical model of the electron is suggested according to the basic structures of matter (BSM) hypothesis. BSM is based on an alternative concept about the physical vacuum, assuming that space contains an underlying grid structure of nodes formed of superdense subelementary particles, which are also involved in the structure of the elementary particles. The proposed grid structure is formed of vibrating nodes that possess quantum features and energy well. It is admitted that this hypothetical structure could account for the (...) missing “dark matter” in the universe. The signature of this dark matter is apparent in the galactic rotational curves and in the relation between masses of the supermassive black hole in the galactic center and the host galaxy. The suggested model of the electron possesses oscillation features with anomalous magnetic moment and embedded signatures of the Compton wavelength and the fine-structure constant. The analysis of the interactions between the oscillating electron and the nodes of the vacuum grid structure allows us to obtain physical meaning for some fundamental constants. (shrink)

The modern abundance and prominence of data has led to the development of “data science” as a new field of enquiry, along with a body of epistemological reflections upon its foundations, methods, and consequences. This article provides a systematic analysis and critical review of significant open problems and debates in the epistemology of data science. We propose a partition of the epistemology of data science into the following five domains: (i) the constitution of data science; (ii) the kind of enquiry (...) that it identifies; (iii) the kinds of knowledge that data science generates; (iv) the nature and epistemological significance of “black box” problems; and (v) the relationship between data science and the philosophy of science more generally. (shrink)

This contribution aims to explore the historical predecessors of the Five Percenter model of self-realization, as popularized by Hip Hop artists such as Supreme Team, Rakim Allah, Brand Nubian, Wu-Tang Clan, or Sunz of Man. As compared to frequent considerations of the phenomenon as a creative mythological background for a socio-political struggle, Five Percenter teachings shall be discussed as contemporary interpretations of historical models of self-realization in various philosophical, religious, and esoteric systems. By putting the coded system of the (...) tenfold Supreme Mathematics as one of its core teachings in context with the Pythagorean Tetractys, an arrangement of ten points in four lines, the commonalities between the sequence and concepts attributed to the respective numbers will be demonstrated. (shrink)

I defend an empirically-oriented approach to the analysis and remediation of social injustice. My springboard for this argument is a debate—principally represented here between Tommie Shelby and Elizabeth Anderson, but with much deeper historical roots and many flowering branches—about whether racial-justice advocacy should prioritize integration (bringing different groups together) or community development (building wealth and political power within the black community). Although I incline toward something closer to Shelby’s “egalitarian pluralist” approach over Anderson’s single-minded emphasis on integration, many of (...) Shelby’s criticisms of integrationism are misguided, and his handling of the empirical literature is profoundly unbalanced. In fact, while both Shelby and Anderson defend the importance of social science to their projects, I’ll argue that each takes a decidedly unempirical approach, which ultimately obscures the full extent of our ignorance about what we can and ought to do going forward. A more authentically empirical tack would be more epistemically humble, more holistic, and less organized around what I’ll call prematurely formulated “Grand Unified Theories of Social Change.” I defend a more “diversified experimentalist” approach, which rigorously tests an array of smaller-scale interventions before trying to replicate and scale up the most promising results. (shrink)