Abstract-Deep neural networks have achieved near-human accuracy levels in various types of classification and prediction tasks including images, text, speech, and video data. However, the networks continue to be treated mostly as black-box function approximators, mapping a given input to a classification output. The next step in this human-machine evolutionary processincorporating these networks into mission critical processes such as medical diagnosis, planning and control -requires a level of trust association with the machine output.Typically, statistical metrics are used to quantify the uncertainty of an output. However, the notion of trust also depends on the visibility that a human has into the working of the machine. In other words, the neural network should provide humanunderstandable justifications for its output leading to insights about the inner workings. We call such models as interpretable deep networks.Interpretability is not a monolithic notion. In fact, the subjectivity of an interpretation, due to different levels of human understanding, implies that there must be a multitude of dimensions that together constitute interpretability. In addition, the interpretation itself can be provided either in terms of the lowlevel network parameters, or in terms of input features used by the model. In this paper, we outline some of the dimensions that are useful for model interpretability, and categorize prior work along those dimensions. In the process, we perform a gap analysis of what needs to be done to improve model interpretability.

There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general consensus over what is meant by 'explainable' and 'interpretable'. In this paper, we argue that this lack of consensus is due to there being several distinct stakeholder communities. We note that, while the concerns of the individual communities are broadly compatible, they are not identical, which gives rise to different intents and requirements for explainability/interpretability. We use the software engineering distinction between validation and verification, and the epistemological distinctions between knowns/unknowns, to tease apart the concerns of the stakeholder communities and highlight the areas where their foci overlap or diverge. It is not the purpose of the authors of this paper to 'take sides' -we count ourselves as members, to varying degrees, of multiple communities -but rather to help disambiguate what stakeholders mean when they ask 'Why?' of an AI.

No abstract

Artificial intelligence (AI) systems hold great promise as decision-support tools, but we must be able to identify and understand their inevitable mistakes if they are to fulfill this potential. This is particularly true in domains where the decisions are high-stakes, such as law, medicine, and the military. In this Perspective, we describe the particular challenges for AI decision support posed in military coalition operations. These include having to deal with limited, low-quality data, which inevitably compromises AI performance. We suggest that these problems can be mitigated by taking steps that allow rapid trust calibration so that decision makers understand the AI system's limitations and likely failures and can calibrate their trust in its outputs appropriately. We propose that AI services can achieve this by being both interpretable and uncertainty-aware. Creating such AI systems poses various technical and human factors challenges. We review these challenges and recommend directions for future research.

Abstract. Query formulation is a key aspect of information retrieval, contributing to both the efficiency and usability of many semantic applications. A number of query languages, such as SPARQL, have been developed for the Semantic Web; however, there are, as yet, few tools to support end users with respect to the creation and editing of semantic queries. In this paper we introduce NITELIGHT, a Web-based graphical tool for semantic query construction that is based on the W3C SPARQL specification. NITELIGHT combines a number of features to support end-users with respect to the creation of SPARQL queries. These include a columnar ontology browser, an interactive graphical design surface, a SPARQL-compliant visual query language, a SPARQL syntax viewer and an integrated semantic query results browser. The functionality of each of these components is described in the current paper. In addition, we discuss the potential contribution of the NITELIGHT tool to rule creation/editing and semantic integration capabilities.