Strong intelligent machines powered by deep neural networks are increasingly deployed as black boxes to make decisions in risk-sensitive domains, such as finance and medical. To reduce potential risk and build trust with users, it is critical to interpret how such machines make their decisions. Existing works interpret a pre-trained neural network by analyzing hidden neurons, mimicking pre-trained models or approximating local predictions. However, these methods do not provide a guarantee on the exactness and consistency of their interpretation. In this paper, we propose an elegant closed form solution named $OpenBox$ to compute exact and consistent interpretations for the family of Piecewise Linear Neural Networks (PLNN). The major idea is to first transform a PLNN into a mathematically equivalent set of linear classifiers, then interpret each linear classifier by the features that dominate its prediction. We further apply $OpenBox$ to demonstrate the effectiveness of non-negative and sparse constraints on improving the interpretability of PLNNs. The extensive experiments on both synthetic and real world data sets clearly demonstrate the exactness and consistency of our interpretation.

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal learning goals and environmental constraints externally imposed, all within its objective function. Experiments are conducted on a concept learning task to test generalization of the proposed algorithm to different environmental conditions and analyze how time and resource constraints impact efficacy of solving the learning problem. Our findings show the environmentally-aware learning agent is able to statistically outperform all other active learners explored under most of the constrained conditions. A key implication is adaptation for active learning agents to more realistic human environments, where constraints are often externally imposed on the learner.

More and more AI services are provided through APIs on cloud where predictive models are hidden behind APIs. To build trust with users and reduce potential application risk, it is important to interpret how such predictive models hidden behind APIs make their decisions. The biggest challenge of interpreting such predictions is that no access to model parameters or training data is available. Existing works interpret the predictions of a model hidden behind an API by heuristically probing the response of the API with perturbed input instances. However, these methods do not provide any guarantee on the exactness and consistency of their interpretations. In this paper, we propose an elegant closed form solution named \texttt{OpenAPI} to compute exact and consistent interpretations for the family of Piecewise Linear Models (PLM), which includes many popular classification models. The major idea is to first construct a set of overdetermined linear equation systems with a small set of perturbed instances and the predictions made by the model on those instances. Then, we solve the equation systems to identify the decision features that are responsible for the prediction on an input instance. Our extensive experiments clearly demonstrate the exactness and consistency of our method.

Autonomy and agency are a central property in robotic systems, human-machine interfaces, e-business, ambient intelligence and assisted living applications. As the complexity of the situations the autonomous agents may encounter in such contexts is increasing, the decisions those agents make must integrate new issues, e.g. decisions involving contextual ethical considerations. Consequently contributions have proposed recommendations, advice or hard-wired ethical principles for systems of autonomous agents. However, socio-technical systems are more and more open and decentralized, and involve autonomous artificial agents interacting with other agents, human operators or users. For such systems, novel and original methods are needed to address contextual ethical decision-making, as decisions are likely to interfere with one another. This paper aims at presenting the ETHICAA project (Ethics and Autonomous Agents) whose objective is to define what should be an autonomous entity that could manage ethical conflicts. As a first proposal, we present various practical case studies of ethical conflicts and highlight what their main system and decision features are.