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

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

In this paper we make the case for the emergence of novel kind of bias with the use of algorithmic decision-making systems. We argue that the distinctive generative process of feature creation, characteristic of machine learning (ML), contorts feature parameters in ways that can lead to emerging feature spaces that encode novel algorithmic bias involving already marginalized groups. We term this bias _assembled bias._ Moreover, assembled biases are distinct from the much-discussed algorithmic bias, both in source (training data versus feature (...) creation) and in content (mimics of extant societal bias versus reconfigured categories). As such, this problem is distinct from issues arising from bias-encoding training feature sets or proxy features. Assembled bias is not epistemically transparent in source or content. Hence, when these ML models are used as a basis for decision-making in social contexts, algorithmic fairness concerns are compounded. (shrink)

The ‘black box problem’ is a long-standing talking point in debates about artificial intelligence. This is a significant point of tension between ethicists, programmers, clinicians and anyone else working on developing AI for healthcare applications. However, the precise definition of these systems are often left undefined, vague, unclear or are assumed to be standardised within AI circles. This leads to situations where individuals working on AI talk over each other and has been invoked in numerous debates between opaque and explainable (...) systems. This paper proposes a coherent and clear definition for the black box problem to assist in future discussions about AI in healthcare. This is accomplished by synthesising various definitions in the literature and examining several criteria that can be extrapolated from these definitions. There are no data in this work. (shrink)

With automation of routine decisions coupled with more intricate and complex information architecture operating this automation, concerns are increasing about the trustworthiness of these systems. These concerns are exacerbated by a class of artificial intelligence that uses deep learning, an algorithmic system of deep neural networks, which on the whole remain opaque or hidden from human comprehension. This situation is commonly referred to as the black box problem in AI. Without understanding how AI reaches its conclusions, it is an open (...) question to what extent we can trust these systems. The question of trust becomes more urgent as we delegate more and more decision-making to and increasingly rely on AI to safeguard significant human goods, such as security, healthcare, and safety. Models that “open the black box” by making the non-linear and complex decision process understandable by human observers are promising solutions to the black box problem in AI but are limited, at least in their current state, in their ability to make these processes less opaque to most observers. A philosophical analysis of trust will show why transparency is a necessary condition for trust and eventually for judging AI to be trustworthy. A more fruitful route for establishing trust in AI is to acknowledge that AI is situated within a socio-technical system that mediates trust, and by increasing the trustworthiness of these systems, we thereby increase trust in AI. (shrink)

Certain characteristics make machine learning a powerful tool for processing large amounts of data, and also particularly unsuitable for explanatory purposes. There are worries that its increasing use in science may sideline the explanatory goals of research. We analyze the key characteristics of ML that might have implications for the future directions in scientific research: epistemic opacity and the ‘theory-agnostic’ modeling. These characteristics are further analyzed in a comparison of ML with the traditional statistical methods, in order to demonstrate what (...) it is specifically that makes ML methodology substantially unsuitable for reaching explanations. The analysis is given broader philosophical context by connecting it with the views on the role of prediction and explanation in science, their relationship, and the value of explanation. We proceed to show, first, that ML disrupts the relationship between prediction and explanation commonly understood as a functional relationship. Then we show that the value of explanation is not exhausted in purely predictive functions, but rather has a ubiquitously recognized value for both science and everyday life. We then invoke two hypothetical scenarios with different degrees of automatization of science, which help test our intuitions on the role of explanation in science. The main question we address is whether ML will reorient or otherwise impact our standard explanatory practice. We conclude with a prognosis that ML would diversify science into purely predictively oriented research based on ML-like techniques and, on the other hand, remaining faithful to anthropocentric research focused on the search for explanation. (shrink)

Some machine learning models, in particular deep neural networks, are not very well understood; nevertheless, they are frequently used in science. Does this lack of understanding pose a problem for using DNNs to understand empirical phenomena? Emily Sullivan has recently argued that understanding with DNNs is not limited by our lack of understanding of DNNs themselves. In the present paper, we will argue, contra Sullivan, that our current lack of understanding of DNNs does limit our ability to understand with DNNs. (...) Sullivan’s claim hinges on which notion of understanding is at play. If we employ a weak notion of understanding, then her claim is tenable, but rather weak. If, however, we employ a strong notion of understanding, particularly explanatory understanding, then her claim is not tenable. (shrink)

The need for fair and just AI is often related to the possibility of understanding AI itself, in other words, of turning an opaque box into a glass box, as inspectable as possible. Transparency and explainability, however, pertain to the technical domain and to philosophy of science, thus leaving the ethics and epistemology of AI largely disconnected. To remedy this, we propose an integrated approach premised on the idea that a glass-box epistemology should explicitly consider how to incorporate values and (...) other normative considerations, such as intersectoral vulnerabilities, at critical stages of the whole process from design and implementation to use and assessment. To connect ethics and epistemology of AI, we perform a double shift of focus. First, we move from trusting the output of an AI system to trusting the process that leads to the outcome. Second, we move from expert assessment to more inclusive assessment strategies, aiming to facilitate expert and non-expert assessment. Together, these two moves yield a framework usable for experts and non-experts when they inquire into relevant epistemological and ethical aspects of AI systems. We dub our framework ‘epistemology-cum-ethics’ to signal the equal importance of both aspects. We develop it from the vantage point of the designers: how to create the conditions to internalize values into the whole process of design, implementation, use, and assessment of an AI system, in which values (epistemic and non-epistemic) are explicitly considered at each stage and inspectable by every salient actor involved at any moment. (shrink)

Explainable artificial intelligence (XAI) is an emerging, multidisciplinary field of research that seeks to develop methods and tools for making AI systems more explainable or interpretable. XAI researchers increasingly recognise explainability as a context-, audience- and purpose-sensitive phenomenon, rather than a single well-defined property that can be directly measured and optimised. However, since there is currently no overarching definition of explainability, this poses a risk of miscommunication between the many different researchers within this multidisciplinary space. This is the problem we (...) seek to address in this paper. We outline a framework, called Explanatory Pragmatism, which we argue has two attractive features. First, it allows us to conceptualise explainability in explicitly context-, audience- and purpose-relative terms, while retaining a unified underlying definition of explainability. Second, it makes visible any normative disagreements that may underpin conflicting claims about explainability regarding the purposes for which explanations are sought. Third, it allows us to distinguish several dimensions of AI explainability. We illustrate this framework by applying it to a case study involving a machine learning model for predicting whether patients suffering disorders of consciousness were likely to recover consciousness. (shrink)

In the last decades, supervised machine learning has seen the widespread growth of highly complex, non-interpretable models, of which deep neural networks are the most typical representative. Due to their complexity, these models have showed an outstanding performance in a series of tasks, as in image recognition and machine translation. Recently, though, there has been an important discussion over whether those non-interpretable models are able to provide any sort of understanding whatsoever. For some scholars, only interpretable models can provide understanding. (...) More popular, however, is the idea that understanding can come from a careful analysis of the dataset or from the model’s theoretical basis. In this paper, I wish to examine the possible forms of obtaining understanding of such non-interpretable models. Two main strategies for providing understanding are analyzed. The first involves understanding without interpretability, either through external evidence for the model’s inner functioning or through analyzing the data. The second is based on the artificial production of interpretable structures, through three main forms: post hoc models, hybrid models, and quasi-interpretable structures. Finally, I consider some of the conceptual difficulties in the attempt to create explanations for these models, and their implications for understanding. (shrink)

Under the rubric of understanding the problem of explainability of AI in terms of abductive cognition, I propose to review the lessons from AlphaGo and her more powerful successors. As AI players in Baduk have arrived at superhuman level, there seems to be no hope for understanding the secret of their breathtakingly brilliant moves. Without making AI players explainable in some ways, both human and AI players would be less-than omniscient, if not ignorant, epistemic agents. Are we bound to have (...) less explainable AI Baduk players as they make further progress? I shall show that the resolution of this apparent paradox depends on how we understand the crucial distinction between abduction and inference to the best explanation. Some further philosophical issues arising from explainable AI will also be discussed in connection with this distinction. (shrink)

Providing healthcare services frequently involves cognitively demanding tasks, including diagnoses and analyses as well as complex decisions about treatments and therapy. From a global perspective, ethically significant inequalities exist between regions where the expert knowledge required for these tasks is scarce or abundant. One possible strategy to diminish such inequalities and increase healthcare opportunities in expert-scarce settings is to provide healthcare solutions involving digital technologies that do not necessarily require the presence of a human expert, e.g., in the form of (...) artificial intelligent decision-support systems (AI-DSS). Such algorithmic decision-making, however, is mostly developed in resource- and expert-abundant settings to support healthcare experts in their work. As a practical consequence, the normative standards and requirements for such algorithmic decision-making in healthcare require the technology to be at least as explainable as the decisions made by the experts themselves. The goal of providing healthcare in settings where resources and expertise are scarce might come with a normative pull to lower the normative standards of using digital technologies in order to provide at least some healthcare in the first place. We scrutinize this tendency to lower standards in particular settings from a normative perspective, distinguish between different types of absolute and relative, local and global standards of explainability, and conclude by defending an ambitious and practicable standard of local relative explainability. (shrink)

The goal of the paper is to develop and propose a general model of the state space of AI. Given the breathtaking progress in AI research and technologies in recent years, such conceptual work is of substantial theoretical interest. The present AI hype is mainly driven by the triumph of deep learning neural networks. As the distinguishing feature of such networks is the ability to self-learn, self-learning is identified as one important dimension of the AI state space. Another dimension is (...) recognized as generalization, the possibility to go over from specific to more general types of problems. A third dimension is semantic grounding. Our overall analysis connects to a number of known foundational issues in the philosophy of mind and cognition: the blockhead objection, the Turing test, the symbol grounding problem, the Chinese room argument, and use theories of meaning. It shall finally be argued that the dimension of grounding decomposes into three sub-dimensions. And the dimension of self-learning turns out as only one of a whole range of “self-x-capacities” (based on ideas of organic computing) that span the self-x-subspace of the full AI state space. (shrink)

The increasing use of Artificial Intelligence for making decisions in public affairs has sparked a lively debate on the benefits and potential harms of self-learning technologies, ranging from the hopes of fully informed and objectively taken decisions to fear for the destruction of mankind. To prevent the negative outcomes and to achieve accountable systems, many have argued that we need to open up the “black box” of AI decision-making and make it more transparent. Whereas this debate has primarily focused on (...) how transparency can secure high-quality, fair, and reliable decisions, far less attention has been devoted to the role of transparency when it comes to how the general public come to perceive AI decision-making as legitimate and worthy of acceptance. Since relying on coercion is not only normatively problematic but also costly and highly inefficient, perceived legitimacy is fundamental to the democratic system. This paper discusses how transparency in and about AI decision-making can affect the public’s perception of the legitimacy of decisions and decision-makers and produce a framework for analyzing these questions. We argue that a limited form of transparency that focuses on providing justifications for decisions has the potential to provide sufficient ground for perceived legitimacy without producing the harms full transparency would bring. (shrink)

As AI systems become increasingly complex it may become unclear, even to the designer of a system, why exactly a system does what it does. This leads to a lack of trust in AI systems. To solve this, the field of explainable AI has been working on ways to produce explanations of these systems’ behaviors. Many methods in explainable AI, such as LIME, offer only a statistical argument for the validity of their explanations. However, some methods instead study the internal (...) structure of the system and try to find components which can be assigned an interpretation. I believe that these methods provide more valuable explanations than those statistical in nature. I will try to identify which explanations can be considered internal to the system using the Chomskyan notion of tacit knowledge. I argue that each explanation expresses a rule, and through the localization of this rule in the system internals, we can take a system to have tacit knowledge of the rule. I conclude that the only methods which are able to sufficiently establish this tacit knowledge are those along the lines of Olah : 4901–4911, 2017), and therefore they provide explanations with unique strengths. (shrink)

Digital twins for health care have the potential to significantly impact the provision of medical services. In addition to possible use in care, this technology could serve as a conduit by which no...

The paper discusses the role of language and culture in the context of quantitative text analysis in psychological research. It reviews current automatic text analysis methods and approaches from the perspective of the unique challenges that can arise when going beyond the default English language. Special attention is paid to closed-vocabulary approaches and related methods, both from the perspective of cross-cultural research where the analytic process inherently consists of comparing phenomena across cultures and languages and the perspective of generalizability beyond (...) the language and the cultural focus of the original investigation. We highlight the need for a more universal and flexible theoretical and methodological grounding of current research, which includes the linguistic, cultural, and situational specifics of communication, and we provide suggestions for procedures that can be implemented in future studies and facilitate psychological text analysis across languages and cultures. (shrink)

I examine the construction and evaluation of machine learning binary classification models. These models are increasingly used for societal applications such as classifying patients into two categories according to the presence or absence of a certain disease like cancer and heart disease. I argue that the construction of ML classification models involves an optimisation process aiming at the minimization of the inductive risk associated with the intended uses of these models. I also argue that the construction of these models is (...) underdetermined by the available data, and that this makes it necessary for ML modellers to make social value judgments in determining the error costs used in ML optimization. I thus suggest that the assessment of the inductive risk with respect to the social values of the intended users is an integral part of the construction and evaluation of ML classification models. I also discuss the implications of this conclusion for the philosophical debate concerning inductive risk. (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)

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)

In light of recent advances in machine learning for medical applications, the automation of medical diagnostics is imminent. That said, before machine learning algorithms find their way into clinical practice, various problems at the epistemic level need to be overcome. In this paper, we discuss different sources of uncertainty arising for clinicians trying to evaluate the trustworthiness of algorithmic evidence when making diagnostic judgments. Thereby, we examine many of the limitations of current machine learning algorithms (with deep learning in particular) (...) and highlight their relevance for medical diagnostics. Among the problems we inspect are the theoretical foundations of deep learning (which are not yet adequately understood), the opacity of algorithmic decisions, and the vulnerabilities of machine learning models, as well as concerns regarding the quality of medical data used to train the models. Building on this, we discuss different desiderata for an uncertainty amelioration strategy that ensures that the integration of machine learning into clinical settings proves to be medically beneficial in a meaningful way. (shrink)

The problem of epistemic opacity in Artificial Intelligence is often characterised as a problem of intransparent algorithms that give rise to intransparent models. However, the degrees of transparency of an AI model should not be taken as an absolute measure of the properties of its algorithms but of the model’s degree of intelligibility to human users. Its epistemically relevant elements are to be specified on various levels above and beyond the computational one. In order to elucidate this claim, I first (...) contrast computer models and their claims to algorithm-based universality with cybernetics-style analogue models and their claims to structural isomorphism between elements of model and target system. While analogue models aim at perceptually or conceptually accessible model-target relations, computer models give rise to a specific kind of underdetermination in these relations that needs to be addressed in specific ways. I then undertake a comparison between two contemporary AI approaches that, although related, distinctly align with the above modelling paradigms and represent distinct strategies towards model intelligibility: Deep Neural Networks and Predictive Processing. I conclude that their respective degrees of epistemic transparency primarily depend on the underlying purposes of modelling, not on their computational properties. (shrink)

Artificial Intelligence and Machine Learning (AI/ML) models introduce unique considerations when determining their epistemic value. Fortunately, existing work on the epistemic features of AI/ML can...

Developments in Machine Learning (ML) have attracted attention in a wide range of healthcare fields to improve medical practice and the benefit of patients. Particularly, this should be achieved by providing more or less automated decision recommendations to the treating physician. However, some hopes placed in ML for healthcare seem to be disappointed, at least in part, by a lack of transparency or traceability. Skepticism exists primarily in the fact that the physician, as the person responsible for diagnosis, therapy, and (...) care, has no or insufficient insight into how such recommendations are reached. The following paper aims to make understandable the specificity of the deliberative model of a physician-patient relationship that has been achieved over decades. By outlining the (social-)epistemic and inherently normative relationship between physicians and patients, I want to show how this relationship might be altered by non-traceable ML recommendations. With respect to some healthcare decisions, such changes in deliberative practice may create normatively far-reaching challenges. Therefore, in the future, a differentiation of decision-making situations in healthcare with respect to the necessary depth of insight into the process of outcome generation seems essential. (shrink)

The initial successes in recent years in harnessing machine learning technologies to improve medical practice and benefit patients have attracted attention in a wide range of healthcare fields. Particularly, it should be achieved by providing automated decision recommendations to the treating clinician. Some hopes placed in such ML-based systems for healthcare, however, seem to be unwarranted, at least partially because of their inherent lack of transparency, although their results seem convincing in accuracy and reliability. Skepticism arises when the physician as (...) the agent responsible for the implementation of diagnosis, therapy, and care is unable to access the generation of findings and recommendations. There is widespread agreement that, generally, a complete traceability is preferable to opaque recommendations; however, there are differences about addressing ML-based systems whose functioning seems to remain opaque to some degree—even if so-called explicable or interpretable systems gain increasing amounts of interest. This essay approaches the epistemic foundations of ML-generated information specifically and medical knowledge generally to advocate differentiations of decision-making situations in clinical contexts regarding their necessary depth of insight into the process of information generation. Empirically accurate or reliable outcomes are sufficient for some decision situations in healthcare, whereas other clinical decisions require extensive insight into ML-generated outcomes because of their inherently normative implications. (shrink)

Many AI systems that make important decisions are black boxes: how they function is opaque even to their developers. This is due to their high complexity and to the fact that they are trained rather than programmed. Efforts to alleviate the opacity of black box systems are typically discussed in terms of transparency, interpretability, and explainability. However, there is little agreement about what these key concepts mean, which makes it difficult to adjudicate the success or promise of opacity alleviation methods. (...) I argue for a unified account of these key concepts that treats the concept of understanding as fundamental. This allows resources from the philosophy of science and the epistemology of understanding to help guide opacity alleviation efforts. A first significant benefit of this understanding account is that it defuses one of the primary, in-principle objections to post hoc explainable AI (XAI) methods. This “rationalization objection” argues that XAI methods provide mere rationalizations rather than genuine explanations. This is because XAI methods involve using a separate “explanation” system to approximate the original black box system. These explanation systems function in a completely different way than the original system, yet XAI methods make inferences about the original system based on the behavior of the explanation system. I argue that, if we conceive of XAI methods as idealized scientific models, this rationalization worry is dissolved. Idealized scientific models misrepresent their target phenomena, yet are capable of providing significant and genuine understanding of their targets. (shrink)

We argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: Are networks explainable, and if so, what does it mean to explain the output of a network? And what does it mean for a network to be interpretable? We argue that accounts of “explanation” tailored specifically to neural networks have ineffectively reinvented the wheel. In (...) response to, we show how four familiar accounts of explanation apply to neural networks as they would to any scientific phenomenon. We diagnose the confusion about explaining neural networks within the machine learning literature as an equivocation on “explainability,” “understandability” and “interpretability.” To remedy this, we distinguish between these notions, and answer by offering a theory and typology of interpretation in machine learning. Interpretation is something one does to an explanation with the aim of producing another, more understandable, explanation. As with explanation, there are various concepts and methods involved in interpretation: Total or Partial, Global or Local, and Approximative or Isomorphic. Our account of “interpretability” is consistent with uses in the machine learning literature, in keeping with the philosophy of explanation and understanding, and pays special attention to medical artificial intelligence systems. (shrink)

The contention that medical artificial intelligence (AI) should be ‘explainable’ is widespread in contemporary philosophy and in legal and best practice documents. Yet critics argue that ‘explainability’ is not a stable concept; non-explainable AI is often more accurate; mechanisms intended to improve explainability do not improve understanding and introduce new epistemic concerns; and explainability requirements are ad hoc where human medical decision-making is often opaque. A recent ‘political response’ to these issues contends that AI used in high-stakes scenarios, including medical (...) AI, must be explainable to meet basic standards of legitimacy: People are owed reasons for decisions that impact their vital interests, and this requires explainable AI. This article demonstrates why the political response fails. Attending to systemic considerations, as its proponents desire, suggests that the political response is subject to the same criticisms as other arguments for explainable AI and presents new issues. It also suggests that decision-making about non-explainable medical AI can meet public reason standards. The most plausible version of the response amounts to a simple claim that public reason demands reasons why AI is permitted. But that does not actually support explainable AI or respond to criticisms of strong requirements for explainable medical AI. (shrink)

This article examines the complaint that arbitrary algorithmic decisions wrong those whom they affect. It makes three contributions. First, it provides an analysis of what arbitrariness means in this context. Second, it argues that arbitrariness is not of moral concern except when special circumstances apply. However, when the same algorithm or different algorithms based on the same data are used in multiple contexts, a person may be arbitrarily excluded from a broad range of opportunities. The third contribution is to explain (...) why this systemic exclusion is of moral concern and to offer a solution to address it. (shrink)

The use of machine learning instead of traditional models in neuroscience raises significant questions about the epistemic benefits of the newer methods. I draw on the literature on model intelligibility in the philosophy of science to offer some benchmarks for the interpretability of artificial neural networks used as a predictive tool in neuroscience. Following two case studies on the use of ANN’s to model motor cortex and the visual system, I argue that the benefit of providing the scientist with understanding (...) of the brain trades off against the predictive accuracy of the models. This trade-off between prediction and understanding is better explained by a non-factivist account of scientific understanding. (shrink)

This paper traces the empiricist program from early debates between nativism and behaviorism within philosophy, through debates about early connectionist approaches within the cognitive sciences, and up to their recent iterations within the domain of deep learning. We demonstrate how current debates on the nature of cognition via deep network architecture echo some of the core issues from the Chomsky/Quine debate and investigate the strength of support offered by these various lines of research to the empiricist standpoint. Referencing literature from (...) both computer science and philosophy, we conclude that the current state of deep learning does not offer strong encouragement to the empiricist side despite some arguments to the contrary. (shrink)

Given the pervasiveness of AI systems and their potential negative effects on people’s lives (especially among already marginalised groups), it becomes imperative to comprehend what goes on when an AI system generates a result, and based on what reasons, it is achieved. There are consistent technical efforts for making systems more “explainable” by reducing their opaqueness and increasing their interpretability and explainability. In this paper, we explore an alternative non-technical approach towards explainability that complement existing ones. Leaving aside technical, statistical, (...) or data-related issues, we focus on the very conceptual underpinnings of the design decisions made by developers and other stakeholders during the lifecycle of a machine learning project. For instance, the design and development of an app to track snoring to detect possible health risks presuppose some picture or another of “health”, which is a key notion that conceptually underpins the project. We take it as a premise that these key concepts are necessarily present during design and development, albeit perhaps tacitly. We argue that by providing “justificatory explanations” about how the team understands the relevant key concepts behind its design decisions, interested parties could gain valuable insights and make better sense of the workings and outcomes of systems. Using the concept of “health”, we illustrate how a particular understanding of it might influence decisions during the design and development stages of a machine learning project, and how making this explicit by incorporating it into ex-post explanations might increase the explanatory and justificatory power of these explanations. We posit that a greater conceptual awareness of the key concepts that underpin design and development decisions may be beneficial to any attempt to develop explainability methods. We recommend that “justificatory explanations” are provided as technical documentation. These are declarative statements that contain at its simplest: (1) a high-level account of the understanding of the relevant key concepts a team possess related to a project’s main domain, (2) how these understandings drive decision-making during the life-cycle stages, and (3) it gives reasons (which could be implicit in the account) that the person or persons doing the explanation consider to have plausible justificatory power for the decisions that were made during the project. (shrink)

The last 5 years have seen a series of remarkable achievements in deep-neural-network-based artificial intelligence research, and some modellers have argued that their performance compares favourably to human cognition. Critics, however, have argued that processing in deep neural networks is unlike human cognition for four reasons: they are (i) data-hungry, (ii) brittle, and (iii) inscrutable black boxes that merely (iv) reward-hack rather than learn real solutions to problems. This article rebuts these criticisms by exposing comparative bias within them, in the (...) process extracting some more general lessons that may also be useful for future debates. (shrink)

Explainable artificial intelligence (XAI) seeks to produce explanations for those machine learning methods which are deemed opaque. However, there is considerable disagreement about what this means and how to achieve it. Authors disagree on what should be explained (topic), to whom something should be explained (stakeholder), how something should be explained (instrument), and why something should be explained (goal). In this paper, I employ insights from means-end epistemology to structure the field. According to means-end epistemology, different means ought to be (...) rationally adopted to achieve different epistemic ends. Applied to XAI, different topics, stakeholders, and goals thus require different instruments. I call this the means-end account of XAI. The means-end account has a descriptive and a normative component: on the one hand, I show how the specific means-end relations give rise to a taxonomy of existing contributions to the field of XAI; on the other hand, I argue that the suitability of XAI methods can be assessed by analyzing whether they are prescribed by a given topic, stakeholder, and goal. (shrink)

This paper addresses the black-box problem in artificial intelligence (AI), and the related problem of explainability of AI in the legal context. We argue, first, that the black box problem is, in fact, a superficial one as it results from an overlap of four different – albeit interconnected – issues: the opacity problem, the strangeness problem, the unpredictability problem, and the justification problem. Thus, we propose a framework for discussing both the black box problem and the explainability of AI. We (...) argue further that contrary to often defended claims the opacity issue is not a genuine problem. We also dismiss the justification problem. Further, we describe the tensions involved in the strangeness and unpredictability problems and suggest some ways to alleviate them. (shrink)

There is a current debate about if, and in what sense, machine learning systems used in the medical context need to be explainable. Those arguing in favor contend these systems require post hoc explanations for each individual decision to increase trust and ensure accurate diagnoses. Those arguing against suggest the high accuracy and reliability of the systems is sufficient for providing epistemic justified beliefs without the need for explaining each individual decision. But, as we show, both solutions have limitations—and it (...) is unclear either address the epistemic worries of the medical professionals using these systems. We argue these systems do require an explanation, but an institutional explanation. These types of explanations provide the reasons why the medical professional should rely on the system in practice—that is, they focus on trying to address the epistemic concerns of those using the system in specific contexts and specific occasions. But ensuring that these institutional explanations are fit for purpose means ensuring the institutions designing and deploying these systems are transparent about the assumptions baked into the system. This requires coordination with experts and end-users concerning how it will function in the field, the metrics used to evaluate its accuracy, and the procedures for auditing the system to prevent biases and failures from going unaddressed. We contend this broader explanation is necessary for either post hoc explanations or accuracy scores to be epistemically meaningful to the medical professional, making it possible for them to rely on these systems as effective and useful tools in their practices. (shrink)

This paper argues that machine learning and epidemiology are on collision course over causation. The discipline of epidemiology lays great emphasis on causation, while ML research does not. Some epidemiologists have proposed imposing what amounts to a causal constraint on ML in epidemiology, requiring it either to engage in causal inference or restrict itself to mere projection. We whittle down the issues to the question of whether causal knowledge is necessary for underwriting predictions about the outcomes of public health interventions. (...) While there is great plausibility to the idea that it is, conviction that something is impossible does not by itself motivate a constraint to forbid trying. We disambiguate the possible motivations for such a constraint into definitional, metaphysical, epistemological, and pragmatic considerations and argue that “Proceed with caution” is the outcome of each. We then argue that there are positive reasons to proceed, albeit cautiously. Causal inference enforces existing classification schema prior to the testing of associational claims, but associations and classification schema are more plausibly discovered in a back-and-forth process of gaining reflective equilibrium. ML instantiates this kind of process, we argue, and thus offers the welcome prospect of uncovering meaningful new concepts in epidemiology and public health—provided it is not causally constrained. (shrink)

Philosophy Compass, Volume 17, Issue 6, June 2022.

AI systems play an increasingly important role in shaping and regulating the lives of millions of human beings across the world. Calls for greater _transparency_ from such systems have been widespread. However, there is considerable ambiguity concerning what “transparency” actually means, and therefore, what greater transparency might entail. While, according to some debates, transparency requires _seeing through_ the artefact or device, widespread calls for transparency imply _seeing into_ different aspects of AI systems. These two notions are in apparent tension with (...) each other, and they are present in two lively but largely disconnected debates. In this paper, we aim to further analyse what these calls for transparency entail, and in so doing, clarify the sorts of transparency that we should want from AI systems. We do so by offering a taxonomy that classifies different notions of transparency. After a careful exploration of the different varieties of transparency, we show how this taxonomy can help us to navigate various domains of human–technology interactions, and more usefully discuss the relationship between technological transparency and human agency. We conclude by arguing that all of these different notions of transparency should be taken into account when designing more ethically adequate AI systems. (shrink)

The prospect of including artificial intelligence in clinical decision-making is an exciting next step for some areas of healthcare. This article provides an analysis of the available kinds of AI systems, focusing on macro-level characteristics. This includes examining the strengths and weaknesses of opaque systems and fully explainable systems. Ultimately, the article argues that “grey box” systems, which include some combination of opacity and transparency, ought to be used in healthcare settings.