Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via $\textit{explanations}$, which justify individual model predictions. In this work, we take a step towards reconciling machine explanations with those that humans produce and prefer by taking inspiration from the study of explanation in philosophy, cognitive science, and the social sciences. We identify key aspects in which these human explanations differ from current machine explanations, distill them into a list of desiderata, and formalize them into a framework via the notion of $\textit{weight of evidence}$ from information theory. Finally, we instantiate this framework in two simple applications and show it produces intuitive and comprehensible explanations.

We discuss promising recent contributions on quantifying feature relevance using Shapley values, where we observed some confusion on which probability distribution is the right one for dropped features. We argue that the confusion is based on not carefully distinguishing between observational and interventional conditional probabilities and try a clarification based on Pearl's seminal work on causality. We conclude that unconditional rather than conditional expectations provide the right notion of dropping features in contradiction to the theoretical justification of the software package SHAP . Parts of SHAP are unaffected because unconditional expectations (which we argue to be conceptually right) are used as approximation for the conditional ones, which encouraged others to'improve' SHAP in a way that we believe to be flawed. Further, our criticism concerns TreeExplainer in SHAP, which really uses conditional expectations (without approximating them by unconditional ones).

Explainable artificial intelligence (XAI) is the attempt to make the finding of results of non-linearly programmed systems transparent to avoid so-called black-box processes. The main task of XAI is to make non-linear programmed systems transparent. It offers practical methods to explain AI models, which, for example, correspond to the regulation of the data protection laws of the European Union (DSVGO). The following five methods are listed, which have to make AI models more transparent and understandable. Layer-wise Relevance Propagation (LRP) is a technique that brings such explainability and scales to potentially highly complex deep neural networks.

Surrogate explainers of black-box machine learning predictions are of paramount importance in the field of eXplainable Artificial Intelligence since they can be applied to any type of data (images, text and tabular), are model-agnostic and are post-hoc (i.e., can be retrofitted). The Local Interpretable Model-agnostic Explanations (LIME) algorithm is often mistakenly unified with a more general framework of surrogate explainers, which may lead to a belief that it is the solution to surrogate explainability. In this paper we empower the community to "build LIME yourself" (bLIMEy) by proposing a principled algorithmic framework for building custom local surrogate explainers of black-box model predictions, including LIME itself. To this end, we demonstrate how to decompose the surrogate explainers family into algorithmically independent and interoperable modules and discuss the influence of these component choices on the functional capabilities of the resulting explainer, using the example of LIME.

Artificial Intelligence (AI) is making more decisions for us than ever before. AI is helping us keep our cars on the right lane, helping judges make the right decision, and even deciding who lives or dies on the battlefield. As AI proliferates in our daily lives, there is also a growing fear that humans lose control. The European Commission's current president, Ursula Von der Leyen, has pushed hard to start creating frameworks to regulate the use of AI, resulting in a document guidelining the requirements that AI systems need to meet in order to be trustworthy. One of the key elements of these guidelines is the notion that "AI systems and their decisions should be explained in a manner adapted to the stakeholder concerned." What the European Commission really wants then, is Explainable AI (EAI): an AI where the logic for making the decision, or a summary of the logic is made available.

Most of the available health care diagnostics that use artificial intelligence (AI) function as black boxes--meaning that results do not include any explanation of why the machine thinks a patient has a certain disease or disorder. While AI technologies are extraordinarily powerful, adoption of these algorithms in health care has been slow because doctors and regulators cannot verify their results. However, a new type of algorithm called "explainable AI" (XAI) can be easily understood by humans. As a result, all signs point to XAI being rapidly adopted across health care, making it likely that providers will actually use the associated diagnostics. With advantages over black box AI, Explainable AI (XAI) is likely to be the dominant algorithm in ... [ ] health care.

Artificial intelligence (AI) is one of the most exciting technologies in the world right now. In particular, it's bringing life to ideas that were once just a figment of Hollywood films. However, it has also created polarised viewpoints. Many AI experts are working towards reaping its full potential, while others worry about creating a Black Mirror-esque reality. Perhaps the best way to meet in the middle is by exploring explainable AI.

Most of the available health care diagnostics that use artificial intelligence (AI) function as black boxes--meaning that results do not include any explanation of why the machine thinks a patient has a certain disease or disorder. While AI technologies are extraordinarily powerful, adoption of these algorithms in health care has been slow because doctors and regulators cannot verify their results. However, a new type of algorithm called "explainable AI" (XAI) can be easily understood by humans. As a result, all signs point to XAI being rapidly adopted across health care, making it likely that providers will actually use the associated diagnostics. With advantages over black box AI, Explainable AI (XAI) is likely to be the dominant algorithm in health care.

This article is coauthored by Joy Rimchala and Shir Meir Lador. Rapid adoption of complex machine learning (ML) models in recent years has brought with it a new challenge for today's companies: how to interpret, understand, and explain the reasoning behind these complex models' predictions. Treating complex ML systems as trustworthy black boxes without sanity checking has led to some disastrous outcomes, as evidenced by recent disclosures of gender and racial biases in GenderShades¹. As ML-assisted predictions integrate more deeply into high-stakes decision-making, such as medical diagnoses, recidivism risk prediction, loan approval processes, etc., knowing the root causes of an ML prediction becomes crucial. If we know that certain model predictions reflect bias and are not aligned with our best knowledge and societal values (such as an equal opportunity policy or outcome equity), we can detect these undesirable ML defects, prevent the deployment of such ML systems, and correct model defects.

As for explainable AI, companies that buy AI-driven products look for explainability at a business level, said Arnab Chakraborty, Global managing director of applied intelligence for the U.S. West Coast region at Accenture. "A lot of our clients have to explain to stakeholders how models work," he said. So, the models need to be transparent. Accenture, a multinational professional services firm headquartered in Dublin, Ireland, has its own toolkit to help explain how AI systems work. The toolkit helps the company lay out different parameters that go into a model and how that model influences different APIs, among other things, Chakraborty said.