Since its emergence in the 1960s, Artifcial Intelligence (AI) has grown to conquer many technology products and their felds of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from diferent (...) domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey diferent meanings and are “weighted" diferently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efciency in the defnition of regulations for ethical and reliable AI development. We show how our taxonomy and defnition of interpretable AI difer from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI. (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)

Artificial Psychology (AP) is a highly multidisciplinary field of study in psychology. AP tries to solve problems which occur when psychologists do research and need a robust analysis method. Conventional statistical approaches have deep rooted limitations. These approaches are excellent on paper but often fail to model the real world. Mind researchers have been trying to overcome this by simplifying the models being studied. This stance has not received much practical attention recently. Promoting and improving artificial intelligence helps mind (...) researchers to find a holistic model of mental models. This development achieves this goal by using multiple perspectives and multiple data sets together with interactive, and realistic models. In this book, the methodology of approximate inference in psychological research from a theoretical and practical perspective has been considered. Quantitative variable-oriented methodology and qualitative case-oriented methods are both used to explain the set-oriented methodology and this book combines the precision of quantitative methods with information from qualitative methods. This is a book that many researchers can use to expand and deepen their psychological research and is a book which can be useful to postgraduate students. The reader does not need an in-depth knowledge of mathematics or statistics because statistical and mathematical intuitions are key here and they will be learned through practice. What is important is to understand and use the new application of the methods for finding new, dynamic and realistic interpretations. This book incorporates theoretical fuzzy inference and deep machine learning algorithms in practice. This is the kind of book that we wished we had had when we were students. This book covers at least some of the most important issues in mind research including uncertainty, fuzziness, continuity, complexity and high dimensionality which are inherent to mind data. These are elements of artificial psychology. This book implements models using R software. (shrink)

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)

Artificial intelligence (AI) systems have demonstrated impressive performance across a variety of clinical tasks. However, notoriously, sometimes these systems are 'black boxes'. The initial response in the literature was a demand for 'explainable AI'. However, recently, several authors have suggested that making AI more explainable or 'interpretable' is likely to be at the cost of the accuracy of these systems and that prioritising interpretability in medical AI may constitute a 'lethal prejudice'. In this paper, we defend (...) the value of interpretability in the context of the use of AI in medicine. Clinicians may prefer interpretable systems over more accurate black boxes, which in turn is sufficient to give designers of AI reason to prefer more interpretable systems in order to ensure that AI is adopted and its benefits realised. Moreover, clinicians may be justified in this preference. Achieving the downstream benefits from AI is critically dependent on how the outputs of these systems are interpreted by physicians and patients. A preference for the use of highly accurate black box AI systems, over less accurate but more interpretable systems , may itself constitute a form of lethal prejudice that may diminish the benefits of AI to - and perhaps even harm - patients. (shrink)

Background: Microbiome biomarker discovery for patient diagnosis, prognosis, and risk evaluation is attracting broad interest. Selected groups of microbial features provide signatures that characterize host disease states such as cancer or cardio-metabolic diseases. Yet, the current predictive models stemming from machine learning still behave as black boxes and seldom generalize well. Their interpretation is challenging for physicians and biologists, which makes them difficult to trust and use routinely in the physician-patient decision-making process. Novel methods that provide interpretability (...) and biological insight are needed. Here, we introduce "predomics", an original machine learning approach inspired by microbial ecosystem interactions that is tailored for metagenomics data. It discovers accurate predictive signatures and provides unprecedented interpretability. The decision provided by the predictive model is based on a simple, yet powerful score computed by adding, subtracting, or dividing cumulative abundance of microbiome measurements. -/- Results: Tested on >100 datasets, we demonstrate that predomics models are simple and highly interpretable. Even with such simplicity, they are at least as accurate as state-of-the-art methods. The family of best models, discovered during the learning process, offers the ability to distil biological information and to decipher the predictability signatures of the studied condition. In a proof-of-concept experiment, we successfully predicted body corpulence and metabolic improvement after bariatric surgery using pre-surgery microbiome data. -/- Conclusions: Predomics is a new algorithm that helps in providing reliable and trustworthy diagnostic decisions in the microbiome field. Predomics is in accord with societal and legal requirements that plead for an explainable artificial intelligence approach in the medical field. (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)

Definition of the problem The umbrella term “explicability” refers to the reduction of opacity of artificial intelligence (AI) systems. These efforts are challenging for medical AI applications because higher accuracy often comes at the cost of increased opacity. This entails ethical tensions because physicians and patients desire to trace how results are produced without compromising the performance of AI systems. The centrality of explicability within the informed consent process for medical AI systems compels an ethical reflection on the trade-offs. (...) Which levels of explicability are needed to obtain informed consent when utilizing medical AI? Arguments We proceed in five steps: First, we map the terms commonly associated with explicability as described in the ethics and computer science literature, i.e., disclosure, intelligibility, interpretability, and explainability. Second, we conduct a conceptual analysis of the ethical requirements for explicability when it comes to informed consent. Third, we distinguish hurdles for explicability in terms of epistemic and explanatory opacity. Fourth, this then allows to conclude the level of explicability physicians must reach and what patients can expect. In a final step, we show how the identified levels of explicability can technically be met from the perspective of computer science. Throughout our work, we take diagnostic AI systems in radiology as an example. Conclusion We determined four levels of explicability that need to be distinguished for ethically defensible informed consent processes and showed how developers of medical AI can technically meet these requirements. (shrink)

Le déficit d’explicabilité des techniques d’apprentissage machine (AM) pose des problèmes opérationnels, juridiques et éthiques. Un des principaux objectifs de notre projet est de fournir des explications éthiques des sorties générées par une application fondée sur de l’AM, considérée comme une boîte noire. La première étape de ce projet, présentée dans cet article, consiste à montrer que la validation de ces boîtes noires diffère épistémologiquement de celle mise en place dans le cadre d’une modélisation mathématique et causale d’un phénomène (...) physique. La différence majeure est qu’une méthode d’AM ne prétend pas représenter une causalité entre les paramètres d’entrées, qui peuvent être de plus de haute dimensionnalité, et ceux de sortie. Nous montrons dans cet article l’intérêt de mettre en œuvre les distinctions épistémologiques entre les différentes fonctions épistémiques d’un modèle, d’une part, et entre la fonction épistémique et l’usage d’un modèle, d’autre part. Enfin, la dernière partie de cet article présente nos travaux en cours sur l’évaluation d’une explication, qui peut être plus persuasive qu’informative, ce qui peut ainsi causer des problèmes d’ordre éthique. (shrink)

Le déficit d’explicabilité des techniques d’apprentissage machine (AM) pose des problèmes opérationnels, juridiques et éthiques. Un des principaux objectifs de notre projet est de fournir des explications éthiques des sorties générées par une application fondée sur de l’AM, considérée comme une boîte noire. La première étape de ce projet, présentée dans cet article, consiste à montrer que la validation de ces boîtes noires diffère épistémologiquement de celle mise en place dans le cadre d’une modélisation mathéma- tique et causale d’un (...) phénomène physique. La différence majeure est qu’une méthode d’AM ne prétend pas représenter une causalité entre les paramètres d’entrées et ceux de sortie. Après avoir proposé une clarification et une adaptation des notions d’inter- prétabilité et d’explicabilité telles qu’on les rencontre dans la littérature déjà abondante sur le sujet, nous montrons dans cet article l’intérêt de mettre en œuvre les distinctions épistémologiques entre les différentes fonctions épistémiques d’un modèle, d’une part, et entre la fonction épistémique et l’usage d’un modèle, d’autre part. Enfin, la dernière partie de cet article présente nos travaux en cours sur l’évaluation d’une explication, qui peut être plus persuasive qu’informative, ce qui peut ainsi causer des problèmes d’ordre éthique. (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)

In a recent article, Erasmus, Brunet, and Fisher (2021) argue that Artificial Neural Networks (ANNs) are explainable. They survey four influential accounts of explanation: the Deductive-Nomological model, the Inductive-Statistical model, the Causal-Mechanical model, and the New-Mechanist model. They argue that, on each of these accounts, the features that make something an explanation is invariant with regard to the complexity of the explanans and the explanandum. Therefore, they conclude, the complexity of ANNs (and other Machine Learning models) does (...) not make them less explainable. In this reply, it is argued that Erasmus et al. left out one influential account of explanation from their discussion: the Unificationist model. It is argued that, on the Unificationist model, the features that makes something an explanation is sensitive to complexity. Therefore, on the Unificationist model, ANNs (and other Machine Learning models) are not explainable. It is emphasized that Erasmus et al.’s general strategy is correct. The literature on explainable Artificial Intelligence can benefit by drawing from philosophical accounts of explanation. However, philosophical accounts of explanation do not settle the problem of whether ANNs are explainable because they do not unanimously declare that explanation is invariant with regard to complexity. (shrink)

Integrating medical imaging with computing technologies, such as Artificial Intelligence (AI) and its subsets: Machine learning (ML) and Deep Learning (DL) has advanced into an essential facet of present-day medicine, signaling a pivotal role in diagnostic decision-making and treatment plans (Huang et al., 2023). The significance of medical imaging is escalated by its sustained growth within the realm of modern healthcare (Varoquaux and Cheplygina, 2022). Nevertheless, the ever-increasing volume of medical images compared to the availability of (...) imaging experts. Biomedical experts and radiologists have resulted in a widening disparity, causing an excess and overwhelming workload on these healthcare professionals (Chen et al., 2021). Several studies indicate that the present-day biomedical radiologist is now saddled with the daunting task of interpreting an image almost every 10 seconds to keep pace with the burgeoning clinical demands (McDonald et al., 2015; Hosny et al., 2018; Lantsman et al., 2022). This cognitive drain has invariably led to inevitable consequences such as delays in diagnosis and an amplified risk of diagnostic errors – thus, the biomedical imaging aspect is in dire need of methods that would aid accurate diagnostics and analytics for improved decision making. In this review, the importance of AI-related technologies such as ML and/or DL methods are reviewed in relation to the processing of medical or biomedical images along with their potentials, challenges, and possible suggestions for future studies in the health landscape. The focus will be on machine learning methods associated with the medical field of image classification. (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)

The use of counterfactuals for considerations of algorithmic fairness and explainability is gaining prominence within the machine learning community and industry. This paper argues for more caution with the use of counterfactuals when the facts to be considered are social categories such as race or gender. We review a broad body of papers from philosophy and social sciences on social ontology and the semantics of counterfactuals, and we conclude that the counterfactual approach in machine learning fairness (...) and social explainability can require an incoherent theory of what social categories are. Our findings suggest that most often the social categories may not admit counterfactual manipulation, and hence may not appropriately satisfy the demands for evaluating the truth or falsity of counterfactuals. This is important because the wide- spread use of counterfactuals in machine learning can lead to misleading results when applied in high-stakes domains. Accordingly, we argue that even though counterfactuals play an essential part in some causal inferences, their use for questions of algorithmic fairness and social explanations can create more problems than they resolve. Our positive result is a set of tenets about using counterfactuals for fairness and explanations in machine learning. (shrink)

This paper focuses on two highly publicized formal trade-offs in the field of responsible artificial intelligence (AI) -- between predictive accuracy and fairness and between predictive accuracy and interpretability. These formal trade-offs are often taken by researchers, practitioners, and policy-makers to directly imply corresponding tensions between underlying values. Thus interpreted, the trade-offs have formed a core focus of normative engagement in AI governance, accompanied by a particular division of labor along disciplinary lines. This paper argues against this prevalent (...) interpretation by drawing attention to three sets of considerations that are critical for bridging the gap between these formal trade-offs and their practical impacts on relevant values. I show how neglecting these considerations can distort our normative deliberations, and result in costly and misaligned interventions and justifications. Taken together, these considerations form a sociotechnical framework that could guide those involved in AI governance to assess how, in many cases, we can and should have higher aspirations than the prevalent interpretation of the trade-offs would suggest. I end by drawing out the normative opportunities and challenges that emerge out of these considerations, and highlighting the imperative of interdisciplinary collaboration in fostering responsible AI. (shrink)

The notion of computation has changed the world more than any previous expressions of knowledge. However, as know-how in its particular algorithmic embodiment, computation is closed to meaning. Therefore, computer-based data processing can only mimic life’s creative aspects, without being creative itself. AI’s current record of accomplishments shows that it automates tasks associated with intelligence, without being intelligent itself. Mistaking the abstract for the concrete has led to the religion of “everything is an output of computation”—even the humankind that (...) conceived the computer. The hypostatized role of computers explains the increased dependence on them. The convergence machine called deep learning is only the most recent form through which the deterministic theology of the machine claims more than what it actually is: extremely effective data processing. A proper understanding of complexity, as well as the need to distinguish between the reactive nature of the artificial and the anticipatory nature of the living are suggested as practical responses to the challenges posed by machine theology. (shrink)

Recent years have witnessed intensive efforts to specify which requirements ethical artificial intelligence (AI) must meet. General guidelines for ethical AI consider a varying number of principles important. A frequent novel element in these guidelines, that we have bundled together under the term explicability, aims to reduce the black-box character of machine learning algorithms. The centrality of this element invites reflection on the conceptual relation between explicability and the four bioethical principles. This is important because the application (...) of general ethical frameworks to clinical decision-making entails conceptual questions: Is explicability a free-standing principle? Is it already covered by the well-established four bioethical principles? Or is it an independent value that needs to be recognized as such in medical practice? We discuss these questions in a conceptual-ethical analysis, which builds upon the findings of an empirical document analysis. On the example of the medical specialty of radiology, we analyze the position of radiological associations on the ethical use of medical AI. We address three questions: Are there references to explicability or a similar concept? What are the reasons for such inclusion? Which ethical concepts are referred to? (shrink)

The ongoing explosion of interest in artificial intelligence is fueled in part by recently developed techniques in machine learning. Those techniques allow automated systems to process huge amounts of data, utilizing mathematical methods that depart from traditional statistical approaches, and resulting in impressive advancements in our ability to make predictions and uncover correlations across a host of interesting domains. But as is now widely discussed, the way that those systems arrive at their outputs is often opaque, even (...) to the experts who design and deploy them. Is it morally problematic to make use of opaque automated methods when making high-stakes decisions, like whether to issue a loan to an applicant, or whether to approve a parole request? Many scholars answer in the affirmative. However, there is no widely accepted explanation for why transparent systems are morally preferable to opaque systems. We argue that the use of automated decision-making systems sometimes violates duties of consideration that are owed by decision-makers to decision-subjects, duties that are both epistemic and practical in character. Violations of that kind generate a weighty consideration against the use of opaque decision systems. In the course of defending our approach, we show that it is able to address three major challenges sometimes leveled against attempts to defend the moral import of transparency in automated decision-making. (shrink)

How should a machine intelligence perform unsupervised structure discovery over streams of sensory input? One approach to this problem is to cast it as an apperception task [1]. Here, the task is to construct an explicit interpretable theory that both explains the sensory sequence and also satisfies a set of unity conditions, designed to ensure that the constituents of the theory are connected in a relational structure. However, the original formulation of the apperception task had one fundamental limitation: (...) it assumed the raw sensory input had already been parsed using a set of discrete categories, so that all the system had to do was receive this already-digested symbolic input, and make sense of it. But what if we don't have access to pre-parsed input? What if our sensory sequence is raw unprocessed information? The central contribution of this paper is a neuro-symbolic framework for distilling interpretable theories out of streams of raw, unprocessed sensory experience. First, we extend the definition of the apperception task to include ambiguous (but still symbolic) input: sequences of sets of disjunctions. Next, we use a neural network to map raw sensory input to disjunctive input. Our binary neural network is encoded as a logic program, so the weights of the network and the rules of the theory can be solved jointly as a single SAT problem. This way, we are able to jointly learn how to perceive (mapping raw sensory information to concepts) and apperceive (combining concepts into declarative rules). (shrink)

The paper proposes a synthesis between human scientists and artificial representation learning models as a way of augmenting epistemic warrants of realist theories against various anti-realist attempts. Towards this end, the paper fleshes out unconceived alternatives not as a critique of scientific realism but rather a reinforcement, as it rejects the retrospective interpretations of scientific progress, which brought about the problem of alternatives in the first place. By utilising adversarial machine learning, the synthesis explores possibility spaces of (...) available evidence for unconceived alternatives providing modal knowledge of what is possible therein. As a result, the epistemic warrant of synthesised realist theories should emerge bolstered as the underdetermination by available evidence gets reduced. While shifting the realist commitment away from theoretical artefacts towards modalities of the possibility spaces, the synthesis comes out as a kind of perspectival modelling. (shrink)

Endowing artificial systems with explanatory capacities about the reasons guiding their decisions, represents a crucial challenge and research objective in the current fields of Artificial Intelligence (AI) and Computational Cognitive Science [Langley et al., 2017]. Current mainstream AI systems, in fact, despite the enormous progresses reached in specific tasks, mostly fail to provide a transparent account of the reasons determining their behavior (both in cases of a successful or unsuccessful output). This is due to the fact that the classical (...) problem of opacity in artificial neural networks (ANNs) explodes with the adoption of current Deep Learning techniques [LeCun, Bengio, Hinton, 2015]. In this paper we argue that the explanatory deficit of such techniques represents an important problem, that limits their adoption in the cognitive modelling and computational cognitive science arena. In particular we will show how the current attempts of providing explanations of the deep nets behaviour (see e.g. [Ritter et al. 2017] are not satisfactory. As a possibile way out to this problem, we present two different research strategies. The first strategy aims at dealing with the opacity problem by providing a more abstract interpretation of neural mechanisms and representations. This approach is adopted, for example, by the biologically inspired SPAUN architecture [Eliasmith et al., 2012] and by other proposals suggesting, for example, the interpretation of neural networks in terms of the Conceptual Spaces framework [Gärdenfors 2000, Lieto, Chella and Frixione, 2017]. All such proposals presuppose that the neural level of representation can be considered somehow irrelevant for attacking the problem of explanation [Lieto, Lebiere and Oltramari, 2017]. In our opinion, pursuing this research direction can still preserve the use of deep learning techniques in artificial cognitive models provided that novel and additional results in terms of “transparency” are obtained. The second strategy is somehow at odds with respect to the previous one and tries to address the explanatory issue by avoiding to directly solve the “opacity” problem. In this case, the idea is that one of resorting to pre-compiled plausible explanatory models of the word used in combination with deep-nets (see e.g. [Augello et al. 2017]). We argue that this research agenda, even if does not directly fits the explanatory needs of Computational Cognitive Science, can still be useful to provide results in the area of applied AI aiming at shedding light on the models of interaction between low level and high level tasks (e.g. between perceptual categorization and explanantion) in artificial systems. (shrink)

This is our journal for developing Deduction Theory and studying Deep Learning and Artificial intelligence. Deduction Theory is a Theory of Deducing World’s Relativity by Information Coupling and Asymmetry. We focus on information processing, see intelligence as an information structure that relatively close object-oriented, probability-oriented, unsupervised learning, relativity information processing and massive automated information processing. We see deep learning and machine learning as an attempt to make all types of information processing relatively close (...) to probability information processing. We will discuss about how to understand Deep Learning and Artificial intelligence and why Deep Learning is shown better performance than the other methods by metaphysical logic. (shrink)

The increasing application of artificial intelligence (AI) to healthcare raises both hope and ethical concerns. Some advanced machine learning methods provide accurate clinical predictions at the expense of a significant lack of explainability. Alex John London has defended that accuracy is a more important value than explainability in AI medicine. In this article, we locate the trade-off between accurate performance and explainable algorithms in the context of distributive justice. We acknowledge that accuracy is cardinal from outcome-oriented (...) justice because it helps to maximize patients’ benefits and optimizes limited resources. However, we claim that the opaqueness of the algorithmic black box and its absence of explainability threatens core commitments of procedural fairness such as accountability, avoidance of bias, and transparency. To illustrate this, we discuss liver transplantation as a case of critical medical resources in which the lack of explainability in AI-based allocation algorithms is procedurally unfair. Finally, we provide a number of ethical recommendations for when considering the use of unexplainable algorithms in the distribution of health-related resources. (shrink)

This article addresses computational procedures that are no longer constrained by human modes of representation and considers how these procedures could be philosophically understood in terms of ‘algorithmic thought’. Research in deep learning is its case study. This artificial intelligence (AI) technique operates in computational ways that are often opaque. Such a black-box character demands rethinking the abstractive operations of deep learning. The article does so by entering debates about explainability in AI and assessing how technoscience and (...) technoculture tackle the possibility to ‘re-present’ the algorithmic procedures of feature extraction and feature learning to the human mind. The article thus mobilises the notion of incommensurability (originally developed in the philosophy of science) to address explainability as a communicational and representational issue, which challenges phenomenological and existential modes of comparison between human and algorithmic ‘thinking’ operations. (shrink)

Why would we want to develop artificial human-like arithmetical intelligence, when computers already outperform humans in arithmetical calculations? Aside from arithmetic consisting of much more than mere calculations, one suggested reason is that AI research can help us explain the development of human arithmetical cognition. Here I argue that this question needs to be studied already in the context of basic, non-symbolic, numerical cognition. Analyzing recent machine learning research on artificial neural networks, I show how AI studies (...) could potentially shed light on the development of human numerical abilities, from the proto-arithmetical abilities of subitizing and estimating to counting procedures. Although the current results are far from conclusive and much more work is needed, I argue that AI research should be included in the interdisciplinary toolbox when we try to explain the development and character of numerical cognition and arithmetical intelligence. This makes it relevant also for the epistemology of mathematics. (shrink)

This selective review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the highly plastic biological neural networks of invertebrates and vertebrates. Its potential for adaptive learning and control without supervision, the generation of functional complexity, and control architectures based on (...) self-organization is brought forward. Learning without prior knowledge based on excitatory and inhibitory neural mechanisms accounts for the process through which survival-relevant or task-relevant representations are either reinforced or suppressed. The basic mechanisms of unsupervised biological learning drive synaptic plasticity and adaptation for behavioral success in living brains with different levels of complexity. The insights collected here point toward the Hebbian model as a choice solution for “intelligent” robotics and sensor systems. Keywords: Hebbian learning; synaptic plasticity; neural networks; self-organization; brain; reinforcement; sensory processing; robot control . (shrink)

Modern life sciences research is increasingly relying on artificial intelligence (AI) approaches to model biological systems, primarily centered around the use of machine learning (ML) models. Although ML is undeniably useful for identifying patterns in large, complex data sets, its widespread application in biological sciences represents a significant deviation from traditional methods of scientific inquiry. As such, the interplay between these models and scientific understanding in biology is a topic with important implications for the future of scientific (...) research, yet it is a subject that has received little attention. Here, we draw from an epistemological toolkit to contextualize recent applications of ML in biological sciences under modern philosophical theories of understanding, identifying general principles that can guide the design and application of ML systems to model biological phenomena and advance scientific knowledge. We propose that conceptions of scientific understanding as information compression, qualitative intelligibility, and dependency relation modelling provide a useful framework for interpreting ML-mediated understanding of biological systems. Through a detailed analysis of two key application areas of ML in modern biological research – protein structure prediction and single cell RNA-sequencing – we explore how these features have thus far enabled ML systems to advance scientific understanding of their target phenomena, how they may guide the development of future ML models, and the key obstacles that remain in preventing ML from achieving its potential as a tool for biological discovery. Consideration of the epistemological features of ML applications in biology will improve the prospects of these methods to solve important problems and advance scientific understanding of living systems. (shrink)

The current paradigm of Artificial Intelligence emerged as the result of a series of cultural innovations, some technical and some social. Among them are apparently small design decisions, that led to a subtle reframing of the field’s original goals, and are by now accepted as standard. They correspond to technical shortcuts, aimed at bypassing problems that were otherwise too complicated or too expensive to solve, while still delivering a viable version of AI. Far from being a series of separate (...) problems, recent cases of unexpected effects of AI are the consequences of those very choices that enabled the field to succeed, and this is why it will be difficult to solve them. In this chapter we review three of these choices, investigating their connection to some of today’s challenges in AI, including those relative to bias, value alignment, privacy and explainability. We introduce the notion of “ethical debt” to describe the necessity to undertake expensive rework in the future in order to address ethical problems created by a technical system. (shrink)

Machine intelligence already helps medical staff with a number of tasks. Ethical decision-making, however, has not been handed over to computers. In this proof-of-concept study, we show how an algorithm based on Beauchamp and Childress’ prima-facie principles could be employed to advise on a range of moral dilemma situations that occur in medical institutions. We explain why we chose fuzzy cognitive maps to set up the advisory system and how we utilized machine learning to train it. (...) We report on the difficult task of operationalizing the principles of beneficence, non-maleficence and patient autonomy, and describe how we selected suitable input parameters that we extracted from a training dataset of clinical cases. The first performance results are promising, but an algorithmic approach to ethics also comes with several weaknesses and limitations. Should one really entrust the sensitive domain of clinical ethics to machine intelligence? (shrink)

To create fair and accountable AI and robotics, we need precise regulation and better methods to certify, explain, and audit inscrutable systems.

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 (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. 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 provide a sound and complete algorithm for computing (...) explanatory factors with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on various tasks. (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)

: Driver drowsiness is a significant factor contributing to road accidents, resulting in severe injuries and fatalities. This study presents an optimized approach for detecting driver drowsiness using machine learning techniques. The proposed system utilizes real-time data to analyze driver behavior and physiological signals to identify signs of fatigue. Various machine learning algorithms, including Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Random Forest, are explored for their efficacy in detecting drowsiness. The system incorporates an (...) optimization technique—such as Genetic Algorithms (GA) or Particle Swarm Optimization (PSO)—to enhance the accuracy and response time of the detection process. The integration of optimization methods ensures that the model adapts to various driving conditions and individual differences, providing a more reliable and robust detection mechanism. Data from multiple sources, including camera feeds and wearable sensors, are used to train and validate the models, ensuring a comprehensive understanding of drowsiness indicators. (shrink)

Artificial intelligence (AI) systems have demonstrated impressive performance across a variety of clinical tasks. However, notoriously, sometimes these systems are “black boxes.” The initial response in the literature was a demand for “explainable AI.” However, recently, several authors have suggested that making AI more explainable or “interpretable” is likely to be at the cost of the accuracy of these systems and that prioritizing interpretability in medical AI may constitute a “lethal prejudice.” In this paper, we defend (...) the value of interpretability in the context of the use of AI in medicine. Clinicians may prefer interpretable systems over more accurate black boxes, which in turn is sufficient to give designers of AI reason to prefer more interpretable systems in order to ensure that AI is adopted and its benefits realized. Moreover, clinicians may be justified in this preference. Achieving the downstream benefits from AI is critically dependent on how the outputs of these systems are interpreted by physicians and patients. A preference for the use of highly accurate black box AI systems, over less accurate but more interpretable systems, may itself constitute a form of lethal prejudice that may diminish the benefits of AI to—and perhaps even harm—patients. (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.

The success of deep learning in natural language processing raises intriguing questions about the nature of linguistic meaning and ways in which it can be processed by natural and artificial systems. One such question has to do with subword segmentation algorithms widely employed in language modeling, machine translation, and other tasks since 2016. These algorithms often cut words into semantically opaque pieces, such as ‘period’, ‘on’, ‘t’, and ‘ist’ in ‘period|on|t|ist’. The system then represents the resulting segments in (...) a dense vector space, which is expected to model grammatical relations among them. This representation may in turn be used to map ‘period|on|t|ist’ (English) to ‘par|od|ont|iste’ (French). Thus, instead of being modeled at the lexical level, translation is reformulated more generally as the task of learning the best bilingual mapping between the sequences of subword segments of two languages; and sometimes even between pure character sequences: ‘p|e|r|i|o|d|o|n|t|i|s|t’ → ‘p|a|r|o|d|o|n|t|i|s|t|e’. Such subword segmentations and alignments are at work in highly efficient end-to-end machine translation systems, despite their allegedly opaque nature. The computational value of such processes is unquestionable. But do they have any linguistic or philosophical plausibility? I attempt to cast light on this question by reviewing the relevant details of the subword segmentation algorithms and by relating them to important philosophical and linguistic debates, in the spirit of making artificial intelligence more transparent and explainable. (shrink)

The emerging contemporary natural philosophy provides a common ground for the integrative view of the natural, the artificial, and the human-social knowledge and practices. Learning process is central for acquiring, maintaining, and managing knowledge, both theoretical and practical. This paper explores the relationships between the present advances in understanding of learning in the sciences of the artificial, natural sciences, and philosophy. The question is, what at this stage of the development the inspiration from nature, specifically its computational models (...) such as info-computation through morphological computing, can contribute to machine learning and artificial intelligence, and how much on the other hand models and experiments in machine learning and robotics can motivate, justify, and inform research in computational cognitive science, neurosciences, and computing nature. We propose that one contribution can be understanding of the mechanisms of ‘learning to learn’, as a step towards deep learning with symbolic layer of computation/information processing in a framework linking connectionism with symbolism. As all natural systems possessing intelligence are cognitive systems, we describe the evolutionary arguments for the necessity of learning to learn for a system to reach humanlevel intelligence through evolution and development. The paper thus presents a contribution to the epistemology of the contemporary philosophy of nature. (shrink)

This paper addresses a question about the moral status of Artificial Intelligence (AI): will AIs ever become moral patients? I argue that, while it is in principle possible for an intelligent machine to be a moral patient, there is no good reason to believe this will in fact happen. I start from the plausible assumption that traditional artifacts do not meet a minimal necessary condition of moral patiency: having a good of one's own. I then argue that intelligent (...) machines are no different from traditional artifacts in this respect. To make this argument, I examine the feature of AIs that enables them to improve their intelligence, i.e., machine learning. I argue that there is no reason to believe that future advances in machine learning will take AIs closer to having a good of their own. I thus argue that concerns about the moral status of future AIs are unwarranted. Nothing about the nature of intelligent machines makes them a better candidate for acquiring moral patiency than the traditional artifacts whose moral status does not concern us. (shrink)

Virtue ethics has many times been suggested as a promising recipe for the construction of artificial moral agents due to its emphasis on moral character and learning. However, given the complex nature of the theory, hardly any work has de facto attempted to implement the core tenets of virtue ethics in moral machines. The main goal of this paper is to demonstrate how virtue ethics can be taken all the way from theory to machine implementation. To achieve this (...) goal, we critically explore the possibilities and challenges for virtue ethics from a computational perspective. Drawing on previous conceptual and technical work, we outline a version of artificial virtue based on moral functionalism, connectionist bottom–up learning, and eudaimonic reward. We then describe how core features of the outlined theory can be interpreted in terms of functionality, which in turn informs the design of components necessary for virtuous cognition. Finally, we present a comprehensive framework for the technical development of artificial virtuous agents and discuss how they can be implemented in moral environments. (shrink)

Machine learning systems (MLS) that model low-level processes are the cornerstones of current AI systems. These ‘indirect’ learners are good at classifying kinds that are distinguished solely by their manifest physical properties. But the more a kind is a function of spatio-temporally extended properties — words, situation-types, social norms — the less likely an MLS will be able to track it. Systems that can interact with objects at the individual level, on the other hand, and that can sustain (...) this interaction, can learn responses to increasingly abstract properties, including representational ones. This representational capacity, arguably the mark of intelligence, then, is not available to current MLS’s. (shrink)

This dissertation consists of five chapters, each written as independent research papers that are unified by an overarching concern regarding information privacy and machine learning-based artificial intelligence (AI). This dissertation addresses the issues concerning privacy and AI by responding to the following three main research questions (RQs): RQ1. ‘How does an AI system affect privacy?’; RQ2. ‘How effectively does the General Data Protection Regulation (GDPR) assess and address privacy issues concerning both individuals and groups?’; and RQ3. ‘How (...) can the value of privacy be embedded into systems?’ -/- To respond to the RQs, this dissertation adopts the privacy impact assessment (PIA) as the overall methodology. A PIA encompasses three distinct stages; the first, the analytical stage, concerns the analysis of how AI (particularly focusing on inference as a process that includes inferred information, AI models’ performance, and accessing information uncovered by AI models) impacts privacy. Second, the legal assessment stage concerns whether AI that processes personal information and develops models complies with the GDPR. Finally, the design requirements stage features proposals for design requirements for systems aimed at protecting privacy. Accordingly, this dissertation is structured in three parts, each corresponding to a specific stage of a PIA and responding to one of the RQs. -/- Part I, which addresses the first stage of the PIA, comprises three chapters that altogether respond to RQ1. Chapter 2 analyses how AI impacts the descriptive aspect of privacy; this part argues that AI challenges the current definitions of privacy and that the ‘source control’ and ‘actual access’ definitions of privacy, once revised in the face of counter-examples involving inferred information, converge. Chapter 3, which considers how AI impacts the normative aspect of privacy, particularly the value of privacy, argues that AI affects the social value of privacy, which depends on trust, as this dimension of privacy is constituted when AI models perform accurately. Chapter 4 examines how AI impacts the normative aspect of privacy, particularly the right to privacy, and it argues that, although accessing information uncovered by AI models raises concerns about the privacy of algorithmically designed groups, the right to privacy cannot be recognised for such groups. This is the disruptive feature of AI that has led to consideration of new approaches other than the traditional one, which involves recognising the right to privacy, to protect the privacy of these groups. Instead of recognising the right to privacy for algorithmically designed groups, this chapter suggests taking a moral principle for the moral obligation of protecting vulnerable groups within an ethics of vulnerability. -/- Part II concerns the second stage of the PIA and consists of one chapter that responds to RQ2. Chapter 5, in addition to evaluating whether AI that processes personal information and develops models complies with the GDPR, also assesses whether the GDPR adequately addresses the privacy issues raised by AI. It specifically focuses on group privacy and argues that GDPR has limitations in protecting the privacy of algorithmically designed groups and that the privacy of such vulnerable entities must be considered in the context of privacy and data protection. -/- Part III, which is related to the third stage of the PIA, also consists of one chapter that responds to RQ3. Chapter 6 proposes design requirements to protect privacy by integrating privacy into systems and argues that privacy is instrumentally valuable for the sake of autonomy. Accordingly, to embed the value of privacy into systems, design requirements are articulated through the translation of norms that promote and protect autonomy. (shrink)

Just as humans can draw conclusions responsibly or irresponsibly, so too can computers. Machine learning systems that have been trained on data sets that include irresponsible judgments are likely to yield irresponsible predictions as outputs. In this paper I focus on a particular kind of inference a computer system might make: identification of the intentions with which a person acted on the basis of photographic evidence. Such inferences are liable to be morally objectionable, because of a way in (...) which they are presumptuous. After elaborating this moral concern, I explore the possibility that carefully procuring the training data for image recognition systems could ensure that the systems avoid the problem. The lesson of this paper extends beyond just the particular case of image recognition systems and the challenge of responsibly identifying a person’s intentions. Reflection on this particular case demonstrates the importance (as well as the difficulty) of evaluating machine learning systems and their training data from the standpoint of moral considerations that are not encompassed by ordinary assessments of predictive accuracy. (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)

هدف از پژوهش حاضر، بررسی مسائل اخلاق هوش مصنوعی در حوزۀ هنر است. به‌این‌منظور، با تکیه بر فلسفه و اخلاق هوش مصنوعی، موضوعات اخلاقی که می‌تواند در حوزۀ هنر تأثیرگذار باشد، بررسی شده است. باتوجه‌به رشد و توسعۀ استفاده از هوش مصنوعی و ورود آن به حوزۀ هنر، نیاز است تا مباحث اخلاقی دقیق‌تر مورد توجه پژوهشگران هنر و فلسفه قرار گیرد. برای دست‌یابی به هدف پژوهش، با استفاده از روش تحلیلی‌ـ‌توصیفی، مفاهیمی همچون هوش مصنوعی، برخی تکنیک‌های آن و موضوعات (...) اخلاقی هوش مصنوعی در هنر تبیین و بررسی شده است. نتایج پژوهش نشان می‌دهد موضوعات اخلاقی همچون حریم خصوصی و نظارت، دستکاری در رفتار، تاری و شفافیت، سوگیری در تصمیمات سیستم، و اتوماسیون و اشتغال حوزۀ هنر قابل‌بررسی است. این موضوعات اخلاقی، گاهی درتقابل و گاهی در ارتباط مستقیم و هم‌سو با یکدیگر قرار دارند. بررسی‌ها نشان می‌دهد پاسخ به پرسش‌های اخلاق هوش مصنوعی در حوزۀ هنر، نیازمند پاسخ به پرسش‌های اخلاقی به‌صورت عام در هوش مصنوعی است. The aim of this paper is to explore the ethical implications of artificial intelligence (AI) in the realm of art. Drawing on the philosophy and ethics of AI, this study examines the ethical challenges that may arise in the art domain. Given the increasing use and penetration of AI in the field of art, there is a need for more careful attention to the ethical dimensions of this phenomenon by scholars of art and philosophy. To achieve the objective of the paper, concepts such as AI, some of its techniques, and the ethical issues of AI in art are explained and analyzed using the analytical-descriptive method. The findings of the study reveal that ethical issues such as privacy and surveillance, manipulation of behavior, opacity and transparency, bias in decision systems, and automation and employment can be investigated in the field of art. These ethical issues are sometimes in conflict and sometimes in direct relation with each other. This study suggests that addressing the ethical questions of AI in the field of art requires addressing the ethical questions of AI in general. (shrink)

This paper delves into the use of machine learning-based systems in decision-making processes and its implications for moral responsibility as traditionally defined. It focuses on the emergence of responsibility gaps and examines proposed strategies to address them. The paper aims to provide an introductory and comprehensive overview of the ongoing debate surrounding moral responsibility in automated decision-making. By thoroughly examining these issues, we seek to contribute to a deeper understanding of the implications of AI integration in society.

Today, artificial intelligence, especially machine learning, is structurally dependent on human participation. Technologies such as Deep Learning (DL) leverage networked media infrastructures and human-machine interaction designs to harness users to provide training and verification data. The emergence of DL is therefore based on a fundamental socio-technological transformation of the relationship between humans and machines. Rather than simulating human intelligence, DL-based AIs capture human cognitive abilities, so they are hybrid human-machine apparatuses. From a perspective (...) of media philosophy and social-theoretical critique, I differentiate five types of “media technologies of capture” in AI apparatuses and analyze them as forms of power relations between humans and machines. Finally, I argue that the current hype about AI implies a relational and distributed understanding of (human/artificial) intelligence, which I categorize under the term “cybernetic AI”. This form of AI manifests in socio-technological apparatuses that involve new modes of subjectivation, social control and discrimination of users. (shrink)

Objectives: Machine learning (ML) has the potential to facilitate “continual learning” in medicine, in which an ML system continues to evolve in response to exposure to new data over time, even after being deployed in a clinical setting. In this article, we provide a tutorial on the range of ethical issues raised by the use of such “adaptive” ML systems in medicine that have, thus far, been neglected in the literature. -/- Target audience: The target audiences for (...) this tutorial are the developers of ML AI systems, healthcare regulators, the broader medical informatics community, and practicing clinicians. -/- Scope: Discussions of adaptive ML systems to date have overlooked the distinction between 2 sorts of variance that such systems may exhibit—diachronic evolution (change over time) and synchronic variation (difference between cotemporaneous instantiations of the algorithm at different sites)—and underestimated the significance of the latter. We highlight the challenges that diachronic evolution and synchronic variation present for the quality of patient care, informed consent, and equity, and discuss the complex ethical trade-offs involved in the design of such systems. (shrink)