Predictions obtained by, e.g., artificial neural networks have a high accuracy but humans often perceive the models as black boxes. Insights about the decision making are mostly opaque for humans. Particularly understanding the decision making in highly sensitive areas such as healthcare or fifinance, is of paramount importance. The decision-making behind the black boxes requires it to be more transparent, accountable, and understandable for humans. This survey paper provides essential definitions, an overview of the different principles and methodologies of explainable Supervised Machine Learning (SML). We conduct a state-of-the-art survey that reviews past and recent explainable SML approaches and classifies them according to the introduced definitions. Finally, we illustrate principles by means of an explanatory case study and discuss important future directions.

We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to the outcomes from classification models. They can be applied with black-box models, and also with models that can be specified as logic programs, such as rule-based classifiers. The main focus is on the specification and computation of maximum-responsibility counterfactual explanations, with responsibility becoming an explanation score for features of entities under classification. We also extend the programs to bring into the picture semantic or domain knowledge. We show how the approach could be extended by means of probabilistic methods, and how the underlying probability distributions could be modified through the use of constraints.

With the advent of AI, it has become imperative for the progression of a parallel field, Explainable AI (XAI), to foster trust and human-interpretability in the workings of these intelligent systems. These explanations help the human collaborator understand the circumstances that led to any unexpected behavior in the system and allows the operator to make an informed decision. This article summarizes the paper that demonstrates an approach to generating natural language real-time rationale from autonomous agents in sequential problems and evaluates their humanlike-ness. Using the context of an agent that plays Frogger, a corpus of explanations is collected and fed to a neural rationale generator to produce rationales. These are then studied to measure user perceptions of confidence, humanlike-ness, etc.

FBK is devoted to designing and implementing technology platforms based on artificial intelligence (AI) techniques to make citizens more acquainted managers when it comes to their health and treatment and a more active partner in their interactions with health professionals. In order to achieve this high goal, we combine several excellence skills and push forward the frontier of knowledge within the related disciplinary fields: from NLP techniques to persuasive technologies, from machine learning to taylored software and app development. Such digital technologies can help health system preventing or monitoring diseases. In particultar, through virtual coaching systems that can track changes in day by day patients habits. In this way, people with nutrinional diseases can adopt support tool useful to understand how to progress or manage their diseases.

Therefore, our work alliances through multiple means: diplomatic, economic, seeks to advance capabilities in explainable AI/ML to allow conventional and unconventional warfare, including information a human operative to'calibrate their trust' in an AI/ML asset warfare. A critical requirement for allies is potentially provided by a different coalition partner (Tomsett rapid and continuous integration of capabilities to collect, et al. 2020). The purpose of human-machine teaming is process, disseminate and exploit actionable information and to aim for each party to exploit the strengths of, and compensate intelligence. To achieve this, the MDO layered ISR concept for the weaknesses of, the other (Cummings 2014).

A number of exciting advances have been made in automated fact-checking thanks to increasingly larger datasets and more powerful systems, leading to improvements in the complexity of claims which can be accurately fact-checked. However, despite these advances, there are still desirable functionalities missing from the fact-checking pipeline. In this survey, we focus on the explanation functionality -- that is fact-checking systems providing reasons for their predictions. We summarize existing methods for explaining the predictions of fact-checking systems and we explore trends in this topic. Further, we consider what makes for good explanations in this specific domain through a comparative analysis of existing fact-checking explanations against some desirable properties. Finally, we propose further research directions for generating fact-checking explanations, and describe how these may lead to improvements in the research area.

With the increasing availability of structured and unstructured data and the swift progress of analytical techniques, Artificial Intelligence (AI) is bringing a revolution to the healthcare industry. With the increasingly indispensable role of AI in healthcare, there are growing concerns over the lack of transparency and explainability in addition to potential bias encountered by predictions of the model. This is where Explainable Artificial Intelligence (XAI) comes into the picture. XAI increases the trust placed in an AI system by medical practitioners as well as AI researchers, and thus, eventually, leads to an increasingly widespread deployment of AI in healthcare. In this paper, we present different interpretability techniques. The aim is to enlighten practitioners on the understandability and interpretability of explainable AI systems using a variety of techniques available which can be very advantageous in the health-care domain. Medical diagnosis model is responsible for human life and we need to be confident enough to treat a patient as instructed by a black-box model. Our paper contains examples based on the heart disease dataset and elucidates on how the explainability techniques should be preferred to create trustworthiness while using AI systems in healthcare.

In this paper we show a complete process for unsupervised anomaly detection for the average fuel consumption of fleet vehicles that is able to explain what variables are affecting the consumption in terms of feature relevance. For doing that, we combine the anomaly detection with a surrogate model that is able to provide that feature relevance. For this part, we evaluate both whitebox models from the literature, as well as novel variations over them, and blackbox models combined with local posthoc feature relevance techniques. The evaluation is done using real IoT data belonging to Telef\'onica, and is measured both in terms of model performance, as well as using Explainable AI metrics that compare the explanations generated in terms representativeness, fidelity, stability and contrastiveness. The explanations generate counterfactual recommendations that show what could have been done to reduce the average fuel consumption of a vehicle and turn it into an inlier. The procedure is combined with domain knowledge expressed in business rules, and is able to adequate the type of explanations depending on the target user profile.

In this paper, we discuss necessary and sufficient explanations for formal argumentation - the question whether and why a certain argument can be accepted (or not) under various extension-based semantics. Given a framework with which explanations for argumentation-based conclusions can be derived, we study necessity and sufficiency: what (sets of) arguments are necessary or sufficient for the (non-)acceptance of an argument?

Shapley values underlie one of the most popular model-agnostic methods within explainable artificial intelligence. These values are designed to attribute the difference between a model's prediction and an average baseline to the different features used as input to the model. Being based on solid game-theoretic principles, Shapley values uniquely satisfy several desirable properties, which is why they are increasingly used to explain the predictions of possibly complex and highly non-linear machine learning models. Shapley values are well calibrated to a user's intuition when features are independent, but may lead to undesirable, counterintuitive explanations when the independence assumption is violated. In this paper, we propose a novel framework for computing Shapley values that generalizes recent work that aims to circumvent the independence assumption. By employing Pearl's do-calculus, we show how these 'causal' Shapley values can be derived for general causal graphs without sacrificing any of their desirable properties. Moreover, causal Shapley values enable us to separate the contribution of direct and indirect effects. We provide a practical implementation for computing causal Shapley values based on causal chain graphs when only partial information is available and illustrate their utility on a real-world example.