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 process - incorporating 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 human-understandable 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 low-level 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.

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.

We review the First International Competition on Computational Models of Argumentation (ICCMA'15). The competition evaluated submitted solvers' performance on four different computational tasks related to solving abstract argumentation frameworks. Each task evaluated solvers in ways that pushed the edge of existing performance by introducing new challenges. Despite being the first competition in this area, the high number of competitors entered, and differences in results, suggest that the competition will help shape the landscape of ongoing developments in argumentation theory solvers.