Explainable Artificial Intelligence

This book is about making machine learning models and their decisions interpretable. After exploring the concepts of interpretability, you will learn about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME. All interpretation methods are explained in depth and discussed critically. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.

The development of “intelligent” systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to “intelligent” machines. For sensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner. The 22 chapters included in this book provide a timely snapshot of algorithms, theory, and applications of interpretable and explainable AI and AI techniques that have been proposed recently reflecting the current discourse in this field and providing directions of future development. The book is organized in six parts: towards AI transparency; methods for interpreting AI systems; explaining the decisions of AI systems; evaluating interpretability and explanations; applications of explainable AI; and software for explainable AI.

Over the last decade, progress in deep learning has had a profound and transformational effect on many complex problems, including speech recognition, machine translation, natural language understanding, and computer vision. As a result, computers can now achieve human-competitive performance in a wide range of perception and recognition tasks. Many of these systems are now available to the programmer via a range of so-called cognitive services. More recently, deep reinforcement learning has achieved ground-breaking success in several complex challenges. This book makes an enormous contribution to this beautiful, vibrant area of study: an area that is developing rapidly both in breadth and depth. Deep learning can cope with a broader range of tasks (and perform those tasks to increasing levels of excellence). This book lays a good foundation for the core concepts and principles of deep learning in gaming and animation, walking you through the fundamental ideas with expert ease. This book progresses in a step-by-step manner. It reinforces theory with a full-fledged pedagogy designed to enhance students' understanding and offer them a practical insight into its applications. Also, some chapters introduce and cover novel ideas about how artificial intelligence (AI), deep learning, and machine learning have changed the world in gaming and animation. It gives us the idea that AI can also be applied in gaming, and there are limited textbooks in this area. This book comprehensively addresses all the aspects of AI and deep learning in gaming. Also, each chapter follows a similar structure so that students, teachers, and industry experts can orientate themselves within the text. There are few books in the field of gaming using AI. Deep Learning in Gaming and Animations teaches you how to apply the power of deep learning to build complex reasoning tasks. After being exposed to the foundations of machine and deep learning, you will use Python to build a bot and then teach it the game's rules. This book also focuses on how different technologies have revolutionized gaming and animation with various illustrations.

This book presents Explainable Artificial Intelligence (XAI), which aims at producing explainable models that enable human users to understand and appropriately trust the obtained results. The authors discuss the challenges involved in making machine learning-based AI explainable. Firstly, that the explanations must be adapted to different stakeholders (end-users, policy makers, industries, utilities etc.) with different levels of technical knowledge (managers, engineers, technicians, etc.) in different application domains. Secondly, that it is important to develop an evaluation framework and standards in order to measure the effectiveness of the provided explanations at the human and the technical levels. This book gathers research contributions aiming at the development and/or the use of XAI techniques in order to address the aforementioned challenges in different applications such as healthcare, finance, cybersecurity, and document summarization. It allows highlighting the benefits and requirements of using explainable models in different application domains in order to provide guidance to readers to select the most adapted models to their specified problem and conditions. Includes recent developments of the use of Explainable Artificial Intelligence (XAI) in order to address the challenges of digital transition and cyber-physical systems; Provides a textual scientific description of the use of XAI in order to address the challenges of digital transition and cyber-physical systems; Presents examples and case studies in order to increase transparency and understanding of the methodological concepts.

This book presents that explainable artificial intelligence (XAI) is going to replace the traditional artificial, machine learning, deep learning algorithms which work as a black box as of today. To understand the algorithms better and interpret the complex networks of these algorithms, XAI plays a vital role. In last few decades, we have embraced AI in our daily life to solve a plethora of problems, one of the notable problems is cyber security. In coming years, the traditional AI algorithms are not able to address the zero-day cyber attacks, and hence, to capitalize on the AI algorithms, it is absolutely important to focus more on XAI. Hence, this book serves as an excellent reference for those who are working in cyber security and artificial intelligence.

Explainable artificial intelligence is proficient in operating and analyzing the unconstrainted environment in fields like robotic medicine, robotic treatment, and robotic surgery, which rely on computational vision for analyzing complex situations. Explainable artificial intelligence is a well-structured customizable technology that makes it possible to generate promising unbiased outcomes. The model’s adaptability facilitates the management of heterogeneous healthcare data and the visualization of biological structures through virtual reality. Explainable artificial intelligence has newfound applications in the healthcare industry, such as clinical trial matching, continuous healthcare monitoring, probabilistic evolutions, and evidence-based mechanisms. Principles and Methods of Explainable Artificial Intelligence in Healthcare discusses explainable artificial intelligence and its applications in healthcare, providing a broad overview of state-of-the-art approaches for accurate analysis and diagnosis. The book also encompasses computational vision processing techniques that handle complex data like physiological information, electronic healthcare records, and medical imaging data that assist in earlier prediction. Covering topics such as neural networks and disease detection, this reference work is ideal for industry professionals, practitioners, academicians, researchers, scholars, instructors, and students.

This book provides a full presentation of the current concepts and available techniques to make “machine learning” systems more explainable. The approaches presented can be applied to almost all the current “machine learning” models: linear and logistic regression, deep learning neural networks, natural language processing and image recognition, among the others. Progress in Machine Learning is increasing the use of artificial agents to perform critical tasks previously handled by humans (healthcare, legal and finance, among others). While the principles that guide the design of these agents are understood, most of the current deep-learning models are "opaque" to human understanding. Explainable AI with Python fills the current gap in literature on this emerging topic by taking both a theoretical and a practical perspective, making the reader quickly capable of working with tools and code for Explainable AI. Beginning with examples of what Explainable AI (XAI) is and why it is needed in the field, the book details different approaches to XAI depending on specific context and need. Hands-on work on interpretable models with specific examples leveraging Python are then presented, showing how intrinsic interpretable models can be interpreted and how to produce “human understandable” explanations. Model-agnostic methods for XAI are shown to produce explanations without relying on ML models internals that are “opaque.” Using examples from Computer Vision, the authors then look at explainable models for Deep Learning and prospective methods for the future. Taking a practical perspective, the authors demonstrate how to effectively use ML and XAI in science. The final chapter explains Adversarial Machine Learning and how to do XAI with adversarial examples.

The book proposes techniques, with an emphasis on the financial sector, which will make recommendation systems both accurate and explainable. The vast majority of AI models work like black box models. However, in many applications, e.g., medical diagnosis or venture capital investment recommendations, it is essential to explain the rationale behind AI systems decisions or recommendations. Therefore, the development of artificial intelligence cannot ignore the need for interpretable, transparent, and explainable models. First, the main idea of the explainable recommenders is outlined within the background of neuro-fuzzy systems. In turn, various novel recommenders are proposed, each characterized by achieving high accuracy with a reasonable number of interpretable fuzzy rules. The main part of the book is devoted to a very challenging problem of stock market recommendations. An original concept of the explainable recommender, based on patterns from previous transactions, is developed; it recommends stocks that fit the strategy of investors, and its recommendations are explainable for investment advisers.