We propose a method for generating rule sets as global and local explanations for tree-ensemble learning methods using answer set programming (ASP). To this end, we adopt a decompositional approach where the split structures of the base decision trees are exploited in the construction of rules, which in turn are assessed using pattern mining methods encoded in ASP to extract explanatory rules. For global explanations, candidate rules are chosen from the entire trained tree-ensemble models, whereas for local explanations, candidate rules are selected by only considering rules that are relevant to the particular predicted instance. We show how user-defined constraints and preferences can be represented declaratively in ASP to allow for transparent and flexible rule set generation, and how rules can be used as explanations to help the user better understand the models. Experimental evaluation with real-world datasets and popular tree-ensemble algorithms demonstrates that our approach is applicable to a wide range of classification tasks.

Deep neural networks are said to be opaque, impeding the development of safe and trustworthy artificial intelligence, but where this opacity stems from is less clear. What are the sufficient properties for neural network opacity? Here, I discuss five common properties of deep neural networks and two different kinds of opacity. Which of these properties are sufficient for what type of opacity? I show how each kind of opacity stems from only one of these five properties, and then discuss to what extent the two kinds of opacity can be mitigated by explainability methods.

Detection of defects and identification of symptoms in monitoring industrial systems is a widely studied problem with applications in a wide range of domains. Most of the monitored information extracted from systems corresponds to data series (or time series), where the evolution of values through one or multiple dimensions directly illustrates its health state. Thus, an automatic anomaly detection method in data series becomes crucial. In this article, we propose a novel method based on a convolutional neural network to detect precursors of anomalies in multivariate data series. Our contribution is twofold: We first describe a new convolutional architecture dedicated to multivariate data series classification; We then propose a novel method that returns dCAM, a dimension-wise Class Activation Map specifically designed for multivariate time series that can be used to identify precursors when used for classifying normal and abnormal data series. Experiments with several synthetic datasets demonstrate that dCAM is more accurate than previous classification approaches and a viable solution for discriminant feature discovery and classification explanation in multivariate time series. We then experimentally evaluate our approach on a real and challenging use case dedicated to identifying vibration precursors on pumps in nuclear power plants.

When is it justified to use opaque artificial intelligence (AI) output in medical decision-making? Consideration of this question is of central importance for the responsible use of opaque machine learning (ML) models, which have been shown to produce accurate and reliable diagnoses, prognoses, and treatment suggestions in medicine. In this article, I discuss the merits of two answers to the question. According to the Explanation View, clinicians must have access to an explanation of why an output was produced. According to the Validation View, it is sufficient that the AI system has been validated using established standards for safety and reliability. I defend the Explanation View against two lines of criticism, and I argue that within the framework of evidence-based medicine mere validation seems insufficient for the use of AI output. I end by characterizing the epistemic responsibility of clinicians and point out how a mere AI output cannot in itself ground a practical conclusion about what to do.

Increasingly, laws are being proposed and passed by governments around the world to regulate artificial intelligence (AI) systems implemented into the public and private sectors. Many of these regulations address the transparency of AI systems, and related citizen-aware issues like allowing individuals to have the right to an explanation about how an AI system makes a decision that impacts them. Yet, almost all AI governance documents to date have a significant drawback: they have focused on what to do (or what not to do) with respect to making AI systems transparent, but have left the brunt of the work to technologists to figure out how to build transparent systems. We fill this gap by proposing a stakeholder-first approach that assists technologists in designing transparent, regulatory-compliant systems. We also describe a real-world case study that illustrates how this approach can be used in practice.

A number of governmental and nongovernmental organizations have made significant efforts to encourage the development of artificial intelligence in line with a series of aspirational concepts such as transparency, interpretability, explainability, and accountability. The difficulty at present, however, is that these concepts exist at a fairly abstract level, whereas in order for them to have the tangible effects desired they need to become more concrete and specific. This article undertakes precisely this process of concretisation, mapping how the different concepts interrelate and what in particular they each require in order to move from being high-level aspirations to detailed and enforceable requirements. We argue that the key concept in this process is accountability, since unless an entity can be held accountable for compliance with the other concepts, and indeed more generally, those concepts cannot do the work required of them. There is a variety of taxonomies of accountability in the literature. However, at the core of each account appears to be a sense of “answerability”; a need to explain or to give an account. It is this ability to call an entity to account which provides the impetus for each of the other concepts and helps us to understand what they must each require.

This paper explores a neglected normative dimension of algorithmic opacity in the workplace and the labor market. It argues that explanations of algorithms and algorithmic decisions are of noninstrumental value. That is because explanations of the structure and function of parts of the social world form the basis for reflective clarification of our practical orientation toward the institutions that play a central role in our life. Using this account of the noninstrumental value of explanations, the paper diagnoses distinctive normative defects in the workplace and economic institutions which a reliance on AI can encourage, and which lead to alienation.

AI has had many summers and winters. Proponents have overpromised, and there has been hype and disappointment. In recent years, however, we have watched with awe, surprise, and hope at the successes: Better than human capabilities of image-recognition; winning at Go; useful chatbots that seem to understand your needs; recommendation algorithms harvesting the wisdom of crowds. And with this success comes the spectre of danger. Machine behaviours that embed the worst of human prejudice and biases; techniques trying to exploit human weaknesses to skew elections or prompt self-harming behaviours. Are we seeing a perfect storm of social media, sensor technologies, new algorithms and edge computing? With this backdrop: is AI coming of age?

The paths to digital justice focus on the challenges of contemporary digital societies in reaching automated decision-making processes through software, algorithms, and information technology without loss of its human quality and the guarantees of due process. In this context, this article reflects on the possibilities of establishing judicial robots in substitution for human judges, by examining whether artificial intelligence and algorithms may support judicial decision-making independently and without human supervision. The point of departure for this analysis comes from the experience of criminal justice systems with software for judgment of the possibility of recidivism of criminal defendants. Algorithmic decision-making may improve the public good in support of judicial decision-making, but the analysis of current technology and our standards for due process of law recommends caution on the conclusion that robots may replace human judges and satisfy our expectations for explainability and fairness in adjudication.