Machine learning (ML) techniques have become pervasive across a range of different applications, and are now widely used in areas as disparate as recidivism prediction, consumer credit-risk analysis, and insurance pricing. Likewise, in the physical world, ML models are critical components in autonomous agents such as robotic surgeons and self-driving cars. Among the many ethical dimensions that arise in the use of ML technology in such applications, analyzing morally permissible actions is both immediate and profound. For example, there is the (...) potential for learned algorithms to become biased against certain groups. More generally, in so much that the decisions of ML models impact society, both virtually (e.g., denying a loan) and physically (e.g., driving into a pedestrian), notions of accountability, blame and responsibility need to be carefully considered. In this article, we advocate for a two-pronged approach ethical decision-making enabled using rich models of autonomous agency: on the one hand, we need to draw on philosophical notions of such as beliefs, causes, effects and intentions, and look to formalise them, as attempted by the knowledge representation community, but on the other, from a computational perspective, such theories need to also address the problems of tractable reasoning and (probabilistic) knowledge acquisition. As a concrete instance of this tradeoff, we report on a few preliminary results that apply (propositional) tractable probabilistic models to problems in fair ML and automated reasoning of moral principles. Such models are compilation targets for certain types of knowledge representation languages, and can effectively reason in service some computational tasks. They can also be learned from data. Concretely, current evidence suggests that they are attractive structures for jointly addressing three fundamental challenges: reasoning about possible worlds + tractable computation + knowledge acquisition. Thus, these seems like a good starting point for modelling reasoning robots as part of the larger ecosystem where accountability and responsibility is understood more broadly. (shrink)

Why should moral philosophers, moral psychologists, and machine ethicists care about computational complexity? Debates on whether artificial intelligence (AI) can or should be used to solve problems in ethical domains have mainly been driven by what AI can or cannot do in terms of human capacities. In this paper, we tackle the problem from the other end by exploring what kind of moral machines are possible based on what computational systems can or cannot do. To do so, we analyze normative (...) ethics through the lens of computational complexity. First, we introduce computational complexity for the uninitiated reader and discuss how the complexity of ethical problems can be framed within Marr’s three levels of analysis. We then study a range of ethical problems based on consequentialism, deontology, and virtue ethics, with the aim of elucidating the complexity associated with the problems themselves (e.g., due to combinatorics, uncertainty, strategic dynamics), the computational methods employed (e.g., probability, logic, learning), and the available resources (e.g., time, knowledge, learning). The results indicate that most problems the normative frameworks pose lead to tractability issues in every category analyzed. Our investigation also provides several insights about the computational nature of normative ethics, including the differences between rule- and outcome-based moral strategies, and the implementation-variance with regard to moral resources. We then discuss the consequences complexity results have for the prospect of moral machines in virtue of the trade-off between optimality and efficiency. Finally, we elucidate how computational complexity can be used to inform both philosophical and cognitive-psychological research on human morality by advancing the moral tractability thesis. (shrink)

In the past decade, the fields of machine learning and artificial intelligence (AI) have seen unprecedented developments that raise human-machine interactions (HMI) to the next level.Smart machines, i.e., machines endowed with artificially intelligent systems, have lost their character as mere instruments. This, at least, seems to be the case if one considers how humans experience their interactions with them. Smart machines are construed to serve complex functions involving increasing degrees of freedom, and they generate solutions not fully anticipated by humans. (...) Consequently, their performances show a touch of action and even autonomy. HMI is therefore often described as a sort of “cooperation” rather than as a mere application of a tool. Some authors even go as far as subsuming cooperation with smart machines under the label ofpartnership, akin to cooperation between human agents sharing a common goal. In this paper, we explore how far the notion of shared agency and partnership can take us in our understanding of human interaction with smart machines. Discussing different topoi related to partnerships in general, we suggest that different kinds of “partnership” depending on the form of interaction between agents need to be kept apart. Building upon these discussions, we propose a tentative taxonomy of different kinds of HMI distinguishing coordination, collaboration, cooperation, and social partnership. (shrink)

This paper focuses on the potential of “equitech”—AI technology that improves equity. Recently, interventions have been developed to reduce the harm of implicit bias, the automatic form of stereotype or prejudice that contributes to injustice. However, these interventions—some of which are assisted by AI-related technology—have significant limitations, including unintended negative consequences and general inefficacy. To overcome these limitations, we propose a two-dimensional framework to assess current AI-assisted interventions and explore promising new ones. We begin by using the case of human (...) resource recruitment as a focal point to show that existing approaches have exploited only a subset of the available solution space. We then demonstrate how our framework facilitates the discovery of new approaches. The first dimension of this framework helps us systematically consider the analytic information, intervention implementation, and modes of human-machine interaction made available by advancements in AI-related technology. The second dimension enables the identification and incorporation of insights from recent research on implicit bias intervention. We argue that a design strategy that combines complementary interventions can further enhance the effectiveness of interventions by targeting the various interacting cognitive systems that underlie implicit bias. We end with a discussion of how our cognitive interventions framework can have positive downstream effects for structural problems. (shrink)

Social robotics are autonomous robots or Artificial Moral Agents (AMA), that will interact respect and embody human ethical values. However, the conceptual and practical problems of building such systems have not yet been resolved, playing a role of significant challenge for computational modeling. It seems that the lack of success in constructing robots, ceteris paribus, is due to the conceptual and algorithmic limitations of the current design of ethical robots. This paper proposes a new approach for developing ethical capacities in (...) robotic systems, one based on the concept of Aristotelian phronesis. Phronesis in principle reflexes closer human ethics than the ethical paradigms we employ today in ethical robotics. This paper describes the essential features of phronesis and proposes a high-level architecture for implementing phronetic principles in autonomous robots. Phronetic robotics is in its early stages of conceptualization, so many of the presented ideas are speculative and require further research.2. (shrink)