Artificial Intelligence: Foundations, Theory, and Algorithms - Böcker

In this book, the author examines the ethical implications of Artificial Intelligence systems as they integrate and replace traditional social structures in new sociocognitive-technological environments.

In this book, the author examines the ethical implications of Artificial Intelligence systems as they integrate and replace traditional social structures in new sociocognitive-technological environments.

The principal aim of this book is to introduce to the widest possible audience an original view of belief calculus and uncertainty theory. Part II, The Geometry of Uncertainty, is the core of this book, as it introduces the author’s own geometric approach to uncertainty theory, starting with the geometry of belief functions: Chap.

The principal aim of this book is to introduce to the widest possible audience an original view of belief calculus and uncertainty theory. Part II, The Geometry of Uncertainty, is the core of this book, as it introduces the author’s own geometric approach to uncertainty theory, starting with the geometry of belief functions: Chap.

This open access book provides a comprehensive overview of the state of the art in research and applications of Foundation Models and is intended for readers familiar with basic Natural Language Processing (NLP) concepts. Over the recent years, a revolutionary new paradigm has been developed for training models for NLP. These models are first pre-trained on large collections of text documents to acquire general syntactic knowledge and semantic information. Then, they are fine-tuned for specific tasks, which they can often solve with superhuman accuracy. When the models are large enough, they can be instructed by prompts to solve new tasks without any fine-tuning. Moreover, they can be applied to a wide range of different media and problem domains, ranging from image and video processing to robot control learning. Because they provide a blueprint for solving many tasks in artificial intelligence, they have been called Foundation Models. After a brief introduction to basic NLP models the main pre-trained language models BERT, GPT and sequence-to-sequence transformer are described, as well as the concepts of self-attention and context-sensitive embedding. Then, different approaches to improving these models are discussed, such as expanding the pre-training criteria, increasing the length of input texts, or including extra knowledge. An overview of the best-performing models for about twenty application areas is then presented, e.g., question answering, translation, story generation, dialog systems, generating images from text, etc. For each application area, the strengths and weaknesses of current models are discussed, and an outlook on further developments is given. In addition, links are provided to freely available program code. A concluding chapter summarizes the economic opportunities, mitigation of risks, and potential developments of AI.

This open access book provides a comprehensive overview of the state of the art in research and applications of Foundation Models and is intended for readers familiar with basic Natural Language Processing (NLP) concepts.

Belief change (also referred to as logic of theory change or as belief revision) is a research area that models how rational agents modify their beliefs in response to new information or experiences. It emerged as a major field of study in the mid-1980s and has since become a key topic across disciplines such as philosophy, logic, and artificial intelligence. The one that is nowadays considered the standard model of belief change is the AGM model, proposed by Alchourrón, Gärdenfors and Makinson in the Journal of Symbolic Logic in 1985 (the so-called AGM paper).In the four decades that have followed since, the area has developed rapidly and in many directions. The AGM model inspired many researchers to propose extensions and generalizations (for an overview see Belief Change by Fermé and Hansson, Springer, 2018), from among which the authors highlight the models of non-prioritized belief change: These are models in which the belief change operators considered do not give priority to the new information received (contrary to what is the case regarding the AGM model which fulfils the principle of primacy of new information). For example, the output of a non-prioritized revision may not contain the new belief that has motivated that revision. Analogously, the outcome of a non-prioritized contraction may still contain the sentence by which the contraction is made.In a deep and comprehensive manner, this book summarises the contributions made to the modelling of non-prioritized belief change in the literature from 1985. All models are presented and taxonomized according to their main characteristics.

This book provides a significant step towards bridging the areas of Boolean satisfiability and constraint satisfaction by answering the question why SAT-solvers are efficient on certain classes of CSP instances which are hard to solve for standard constraint solvers. The author also gives theoretical reasons for choosing a particular SAT encoding for several important classes of CSP instances.Boolean satisfiability and constraint satisfaction emerged independently as new fields of computer science, and different solving techniques have become standard for problem solving in the two areas. Even though any propositional formula (SAT) can be viewed as an instance of the general constraint satisfaction problem (CSP), the implications of this connection have only been studied in the last few years.The book will be useful for researchers and graduate students in artificial intelligence and theoretical computer science.

This book offers a coherent and comprehensive approach to feature subset selection in the scope of classification problems, explaining the foundations, real application problems and the challenges of feature selection for high-dimensional data.The authors first focus on the analysis and synthesis of feature selection algorithms, presenting a comprehensive review of basic concepts and experimental results of the most well-known algorithms. They then address different real scenarios with high-dimensional data, showing the use of feature selection algorithms in different contexts with different requirements and information: microarray data, intrusion detection, tear film lipid layer classification and cost-based features. The book then delves into the scenario of big dimension, paying attention to important problems under high-dimensional spaces, such as scalability, distributed processing and real-time processing, scenarios that open up new and interesting challenges for researchers.The book is useful for practitioners, researchers and graduate students in the areas of machine learning and data mining.

This book explains the most prominent and some promising new, general techniques that combine metaheuristics with other optimization methods. A first introductory chapter reviews the basic principles of local search, prominent metaheuristics, and tree search, dynamic programming, mixed integer linear programming, and constraint programming for combinatorial optimization purposes. The chapters that follow present five generally applicable hybridization strategies, with exemplary case studies on selected problems: incomplete solution representations and decoders; problem instance reduction; large neighborhood search; parallel non-independent construction of solutions within metaheuristics; and hybridization based on complete solution archives.     The authors are among the leading researchers in the hybridization of metaheuristics with other techniques for optimization, and their work reflects the broad shift to problem-oriented rather than algorithm-oriented approaches, enabling faster and more effective implementation in real-life applications. This hybridization is not restricted to different variants of metaheuristics but includes, for example, the combination of mathematical programming, dynamic programming, or constraint programming with metaheuristics, reflecting cross-fertilization in fields such as optimization, algorithmics, mathematical modeling, operations research, statistics, and simulation. The book is a valuable introduction and reference for researchers and graduate students in these domains.

This book offers a coherent and comprehensive approach to feature subset selection in the scope of classification problems, explaining the foundations, real application problems and the challenges of feature selection for high-dimensional data.The authors first focus on the analysis and synthesis of feature selection algorithms, presenting a comprehensive review of basic concepts and experimental results of the most well-known algorithms. They then address different real scenarios with high-dimensional data, showing the use of feature selection algorithms in different contexts with different requirements and information: microarray data, intrusion detection, tear film lipid layer classification and cost-based features. The book then delves into the scenario of big dimension, paying attention to important problems under high-dimensional spaces, such as scalability, distributed processing and real-time processing, scenarios that open up new and interesting challenges for researchers.The book is useful for practitioners, researchers and graduate students in the areas of machine learning and data mining.

This book provides a significant step towards bridging the areas of Boolean satisfiability and constraint satisfaction by answering the question why SAT-solvers are efficient on certain classes of CSP instances which are hard to solve for standard constraint solvers.

This is the first comprehensive treatment of subjective logic and all its operations. The author developed the approach, and in this book he first explains subjective opinions, opinion representation, and decision-making under vagueness and uncertainty, and he then offers a full definition of subjective logic, harmonising the key notations and formalisms, concluding with chapters on trust networks and subjective Bayesian networks, which when combined form general subjective networks. The author shows how real-world situations can be realistically modelled with regard to how situations are perceived, with conclusions that more correctly reflect the ignorance and uncertainties that result from partially uncertain input arguments. The book will help researchers and practitioners to advance, improve and apply subjective logic to build powerful artificial reasoning models and tools for solving real-world problems. A good grounding in discrete mathematics is a prerequisite.

This book introduces a novel approach to discrete optimization, providing both theoretical insights and algorithmic developments that lead to improvements over state-of-the-art technology. The authors present chapters on the use of decision diagrams for combinatorial optimization and constraint programming, with attention to general-purpose solution methods as well as problem-specific techniques.The book will be useful for researchers and practitioners in discrete optimization and constraint programming. "Decision Diagrams for Optimization is one of the most exciting developments emerging from constraint programming in recent years. This book is a compelling summary of existing results in this space and a must-read for optimizers around the world." [Pascal Van Hentenryck]

The book discusses the main issues of coordination in complex sociotechnical systems, covering distributed, self-organising, and pervasive systems. A chemistry-inspired model of coordination, a situated architecture and coordination language, and a cognitive model of interaction are the ingredients of the Molecules of Knowledge (MoK) model for self-organisation of knowledge presented in this book. The MoK technology is discussed, along with some case studies in the fields of collaborative systems, academic research, and citizen journalism.The target audience includes researchers and practitioners in the field of complex software systems engineering. The book is also appropriate for graduate and late undergraduate students in computer science and engineering.

The author investigates how to produce realistic and workable ethical codes or regulations in this rapidly developing field to address the immediate and realistic longer-term issues facing us. She spells out the key ethical debates concisely, exposing all sides of the arguments, and addresses how codes of ethics or other regulations might feasibly be developed, looking for pitfalls and opportunities, drawing on lessons learned in other fields, and explaining key points of professional ethics.The book provides a useful resource for those aiming to address the ethical challenges of AI research in meaningful and practical ways.

This book introduces the concept of Electronic Institutions (EIs), where complex interactions between human or software agents are governed by specified rules, mirroring those found in human organisations.

This book explains the most prominent and some promising new, general techniques that combine metaheuristics with other optimization methods. A first introductory chapter reviews the basic principles of local search, prominent metaheuristics, and tree search, dynamic programming, mixed integer linear programming, and constraint programming for combinatorial optimization purposes. The chapters that follow present five generally applicable hybridization strategies, with exemplary case studies on selected problems: incomplete solution representations and decoders; problem instance reduction; large neighborhood search; parallel non-independent construction of solutions within metaheuristics; and hybridization based on complete solution archives.     The authors are among the leading researchers in the hybridization of metaheuristics with other techniques for optimization, and their work reflects the broad shift to problem-oriented rather than algorithm-oriented approaches, enabling faster and more effective implementation in real-life applications. This hybridization is not restricted to different variants of metaheuristics but includes, for example, the combination of mathematical programming, dynamic programming, or constraint programming with metaheuristics, reflecting cross-fertilization in fields such as optimization, algorithmics, mathematical modeling, operations research, statistics, and simulation. The book is a valuable introduction and reference for researchers and graduate students in these domains.

This is the first comprehensive treatment of subjective logic and all its operations. The author developed the approach, and in this book he first explains subjective opinions, opinion representation, and decision-making under vagueness and uncertainty, and he then offers a full definition of subjective logic, harmonising the key notations and formalisms, concluding with chapters on trust networks and subjective Bayesian networks, which when combined form general subjective networks. The author shows how real-world situations can be realistically modelled with regard to how situations are perceived, with conclusions that more correctly reflect the ignorance and uncertainties that result from partially uncertain input arguments. The book will help researchers and practitioners to advance, improve and apply subjective logic to build powerful artificial reasoning models and tools for solving real-world problems. A good grounding in discrete mathematics is a prerequisite.

The authors present chapters on the use of decision diagrams for combinatorial optimization and constraint programming, with attention to general-purpose solution methods as well as problem-specific techniques.The book will be useful for researchers and practitioners in discrete optimization and constraint programming.

The book discusses the main issues of coordination in complex sociotechnical systems, covering distributed, self-organising, and pervasive systems.

The author investigates how to produce realistic and workable ethical codes or regulations in this rapidly developing field to address the immediate and realistic longer-term issues facing us. She spells out the key ethical debates concisely, exposing all sides of the arguments, and addresses how codes of ethics or other regulations might feasibly be developed, looking for pitfalls and opportunities, drawing on lessons learned in other fields, and explaining key points of professional ethics.The book provides a useful resource for those aiming to address the ethical challenges of AI research in meaningful and practical ways.

Representation learning in heterogeneous graphs (HG) is intended to provide a meaningful vector representation for each node so as to facilitate downstream applications such as link prediction, personalized recommendation, node classification, etc. This task, however, is challenging not only because of the need to incorporate heterogeneous structural (graph) information consisting of multiple types of node and edge, but also the need to consider heterogeneous attributes or types of content (e.g. text or image) associated with each node. Although considerable advances have been made in homogeneous (and heterogeneous) graph embedding, attributed graph embedding and graph neural networks, few are capable of simultaneously and effectively taking into account heterogeneous structural (graph) information as well as the heterogeneous content information of each node.In this book, we provide a comprehensive survey of current developments in HG representation learning.More importantly, we present the state-of-the-art in this field, including theoretical models and real applications that have been showcased at the top conferences and journals, such as TKDE, KDD, WWW, IJCAI and AAAI. The book has two major objectives: (1) to provide researchers with an understanding of the fundamental issues and a good point of departure for working in this rapidly expanding field, and (2) to present the latest research on applying heterogeneous graphs to model real systems and learning structural features of interaction systems. To the best of our knowledge, it is the first book to summarize the latest developments and present cutting-edge research on heterogeneous graph representation learning. To gain the most from it, readers should have a basic grasp of computer science, data mining and machine learning.

Representation learning in heterogeneous graphs (HG) is intended to provide a meaningful vector representation for each node so as to facilitate downstream applications such as link prediction, personalized recommendation, node classification, etc. This task, however, is challenging not only because of the need to incorporate heterogeneous structural (graph) information consisting of multiple types of node and edge, but also the need to consider heterogeneous attributes or types of content (e.g. text or image) associated with each node. Although considerable advances have been made in homogeneous (and heterogeneous) graph embedding, attributed graph embedding and graph neural networks, few are capable of simultaneously and effectively taking into account heterogeneous structural (graph) information as well as the heterogeneous content information of each node.In this book, we provide a comprehensive survey of current developments in HG representation learning.More importantly, we present the state-of-the-art in this field, including theoretical models and real applications that have been showcased at the top conferences and journals, such as TKDE, KDD, WWW, IJCAI and AAAI. The book has two major objectives: (1) to provide researchers with an understanding of the fundamental issues and a good point of departure for working in this rapidly expanding field, and (2) to present the latest research on applying heterogeneous graphs to model real systems and learning structural features of interaction systems. To the best of our knowledge, it is the first book to summarize the latest developments and present cutting-edge research on heterogeneous graph representation learning. To gain the most from it, readers should have a basic grasp of computer science, data mining and machine learning.

Machine learning algorithms allow computers to learn without being explicitly programmed. and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers’ awareness of the potential safety issues regarding machine learning models.

Machine learning algorithms allow computers to learn without being explicitly programmed. and adversarial training, which is used to enhance the training process and reduce vulnerabilities. The book aims to improve readers’ awareness of the potential safety issues regarding machine learning models.

This book introduces readers to critical ethical concerns in the development and use of artificial intelligence. Offering clear and accessible information on central concepts and debates in AI ethics, it explores how related problems are now forcing us to address fundamental, age-old questions about human life, value, and meaning. In addition, the book shows how foundational and theoretical issues relate to concrete controversies, with an emphasis on understanding how ethical questions play out in practice.All topics are explored in depth, with clear explanations of relevant debates in ethics and philosophy, drawing on both historical and current sources. Questions in AI ethics are explored in the context of related issues in technology, regulation, society, religion, and culture, to help readers gain a nuanced understanding of the scope of AI ethics within broader debates and concerns.Written with both students and educators in mind, the book is easy to use, with keyterms clearly explained, and numerous exercises designed to stretch and challenge. It offers readers essential insights into the evolving field of AI ethics. Moreover, it presents a range of methods and strategies that can be used to analyse and understand ethical questions, which are illustrated throughout with case studies.

This book introduces readers to critical ethical concerns in the development and use of artificial intelligence. Offering clear and accessible information on central concepts and debates in AI ethics, it explores how related problems are now forcing us to address fundamental, age-old questions about human life, value, and meaning. In addition, the book shows how foundational and theoretical issues relate to concrete controversies, with an emphasis on understanding how ethical questions play out in practice.All topics are explored in depth, with clear explanations of relevant debates in ethics and philosophy, drawing on both historical and current sources. Questions in AI ethics are explored in the context of related issues in technology, regulation, society, religion, and culture, to help readers gain a nuanced understanding of the scope of AI ethics within broader debates and concerns.Written with both students and educators in mind, the book is easy to use, with keyterms clearly explained, and numerous exercises designed to stretch and challenge. It offers readers essential insights into the evolving field of AI ethics. Moreover, it presents a range of methods and strategies that can be used to analyse and understand ethical questions, which are illustrated throughout with case studies.