Explainable AI (XAI) is key to establishing trust among users and fighting the black-box nature of machine learning models. In general, XAI enhances accountability and reliability in machine learning models. For a long time, tech giants like Google, IBM and others have poured resources on explainable AI to explain the decision-making process of such models. Below are the top free resources to understand Explainable AI (XAI) in detail. About: Explainable Machine Learning with LIME and H2O in R is a hands-on, guided introduction to explainable machine learning.

"Trust is a must," she said. "The EU is spearheading the development of new global norms to make sure AI can be trusted. By setting the standards, we can pave the way to ethical technology worldwide." Any fast-moving technology is likely to create mistrust, but Vestager and her colleagues decreed that those in power should do more to tame AI, partly by using such systems more responsibly and being clearer about how these work. The landmark legislation – designed to "guarantee the safety and fundamental rights of people and businesses, while strengthening AI uptake, investment and innovation" – encourages firms to embrace so-called explainable AI.

A pervasive design issue of AI systems is their explainability--how to provide appropriate information to help users understand the AI. The technical field of explainable AI (XAI) has produced a rich toolbox of techniques. Designers are now tasked with the challenges of how to select the most suitable XAI techniques and translate them into UX solutions. Informed by our previous work studying design challenges around XAI UX, this work proposes a design process to tackle these challenges. We review our and related prior work to identify requirements that the process should fulfill, and accordingly, propose a Question-Driven Design Process that grounds the user needs, choices of XAI techniques, design, and evaluation of XAI UX all in the user questions. We provide a mapping guide between prototypical user questions and exemplars of XAI techniques to reframe the technical space of XAI, also serving as boundary objects to support collaboration between designers and AI engineers. We demonstrate it with a use case of designing XAI for healthcare adverse events prediction, and discuss lessons learned for tackling design challenges of AI systems.

Mumbai (Maharashtra) [India], May 7 (ANI/NewsVoir): Since the dawn of the 2000s, Artificial Intelligence (AI) has been making waves through its penetration into various sectors. While AI helps increase efficiency and speed in a system, the lack of feedback when faced with errors has been a glaring concern. Recently developed Explainable Artificial Intelligence (XAI) technology tackles this issue by analyzing data to provide users with explanations for given issues and activities. Utilizing this technology to create investment strategies, Elystar aims to increase net returns by reducing machine/AI-made errors and thereby successfully leveraging the superior insights provided by AI. "Artificial Intelligence in finance is a relatively new concept that is still being explored and experimented upon. While few of the firms experimenting are sparingly using it for short-term trading, we have spent the past 15 months developing models to use it for long-term investments. One simple way to look at this concept is to compare it with Microsoft Excel. While Excel is used in different fields and by different people, it is used in various ways and forms. Similarly, AI has a number of variations in which it can be utilized, so no two approaches may be completely the same. AI not only helps us scale and analyze data rapidly, but the integration of Explainable AI allows us to understand and eliminate unwarranted biases to create a sound investment strategy," said Dr Satya Gautam Vadlamudi, Founder and CEO of Elystar.

To realize autonomous collaborative robots, it is important to increase the trust that users have in them. Toward this goal, this paper proposes an algorithm which endows an autonomous agent with the ability to explain the transition from the current state to the target state in a Markov decision process (MDP). According to cognitive science, to generate an explanation that is acceptable to humans, it is important to present the minimum information necessary to sufficiently understand an event. To meet this requirement, this study proposes a framework for identifying important elements in the decision-making process using a prediction model for the world and generating explanations based on these elements. To verify the ability of the proposed method to generate explanations, we conducted an experiment using a grid environment. It was inferred from the result of a simulation experiment that the explanation generated using the proposed method was composed of the minimum elements important for understanding the transition from the current state to the target state. Furthermore, subject experiments showed that the generated explanation was a good summary of the process of state transition, and that a high evaluation was obtained for the explanation of the reason for an action.

It is commonly claimed that AI will replace most manual labor in the future; however, is this really the case? AI technologies do have higher image recognition accuracy compared to humans in some limited contexts, and have consistently outperformed humans in classical games such as Go and chess. Nonetheless, we believe that even advanced future developments based on current technology will not lead to robots replacing humans. AI systems' fundamental lack of ability to communicate naturally and effectively with humans is among the most significant reasons that they cannot replace human labor. Here, one may believe that such communication could be achieved via the development of natural language processing (NLP) technology [4]; however, NLP technologies are systems for estimating the content of human statements and their meanings; they do not constitute communication. That is, humans do not feel that robots using such systems truly understand and respond to them appropriately. Therefore, if effective communication is not achieved, robots will continue to function only as tools to assist humans. Advancements improving the accuracy or effectiveness of various specific tasks do not indicate that robots are equivalent to human beings. Under this scenario, how can we enable robots to communicate with humans?

In trying to describe phenomenon in the real world, we would need to build models that can closely replicate these events. In general, most modeling approaches could be grouped into two main categories: data-driven or theory-driven solutions. Data-driven approach relies on using data to make sense of the phenomenon around them, but often with limited understanding of the underlying theoretical explanation. For instance, you are told to predict the housing price in a particular neighborhood. You have a good working hypothesis to work with, such as, the size and distance to popular service amenities will have some bearing to the housing price.

In the present paper we present the potential of Explainable Artificial Intelligence methods for decision-support in medical image analysis scenarios. With three types of explainable methods applied to the same medical image data set our aim was to improve the comprehensibility of the decisions provided by the Convolutional Neural Network (CNN). The visual explanations were provided on in-vivo gastral images obtained from a Video capsule endoscopy (VCE), with the goal of increasing the health professionals' trust in the black box predictions. We implemented two post-hoc interpretable machine learning methods LIME and SHAP and the alternative explanation approach CIU, centered on the Contextual Value and Utility (CIU). The produced explanations were evaluated using human evaluation. We conducted three user studies based on the explanations provided by LIME, SHAP and CIU. Users from different non-medical backgrounds carried out a series of tests in the web-based survey setting and stated their experience and understanding of the given explanations. Three user groups (n=20, 20, 20) with three distinct forms of explanations were quantitatively analyzed. We have found that, as hypothesized, the CIU explainable method performed better than both LIME and SHAP methods in terms of increasing support for human decision-making as well as being more transparent and thus understandable to users. Additionally, CIU outperformed LIME and SHAP by generating explanations more rapidly. Our findings suggest that there are notable differences in human decision-making between various explanation support settings. In line with that, we present three potential explainable methods that can with future improvements in implementation be generalized on different medical data sets and can provide great decision-support for medical experts.

An emerging line of research in Explainable NLP is the creation of datasets enriched with human-annotated explanations and rationales, used to build and evaluate models with step-wise inference and explanation generation capabilities. While human-annotated explanations are used as ground-truth for the inference, there is a lack of systematic assessment of their consistency and rigour. In an attempt to provide a critical quality assessment of Explanation Gold Standards (XGSs) for NLI, we propose a systematic annotation methodology, named Explanation Entailment Verification (EEV), to quantify the logical validity of human-annotated explanations. The application of EEV on three mainstream datasets reveals the surprising conclusion that a majority of the explanations, while appearing coherent on the surface, represent logically invalid arguments, ranging from being incomplete to containing clearly identifiable logical errors. This conclusion confirms that the inferential properties of explanations are still poorly formalised and understood, and that additional work on this line of research is necessary to improve the way Explanation Gold Standards are constructed.

A brief overview of the Explainable AI cheat sheet with examples. If you're interested to learn more, this is a non-exhaustive list of links and resources. We'll continue to add more resources. Feel free to suggest valuable resources on the Issues page. Interpretable Machine Learning (IML) - Christoph Molnar Explainability for NLP - Isabelle Augenstein [video] NLP Highlights: Interpreting NLP Model Predictions - Sameer Singh [audio] Please Stop Doing "Explainable" ML - Cynthia Rudin [video]