Cognitive Technologies – serie

Since the last edition of this book (2014), progress has been astonishing in all areas of Natural Language Processing, with recent achievements in Text Generation that spurred a media interest going beyond the traditional academic circles. Text Processing has meanwhile become a mainstream industrial tool that is used, to various extents, by countless companies. As such, a revision of this book was deemed necessary to catch up with the recent breakthroughs, and the author discusses models and architectures that have been instrumental in the recent progress of Natural Language Processing.As in the first two editions, the intention is to expose the reader to the theories used in Natural Language Processing, and to programming examples that are essential for a deep understanding of the concepts. Although present in the previous two editions, Machine Learning is now even more pregnant, having replaced many of the earlier techniques to process text. Many new techniques build on the availability of text. Using Python notebooks, the reader will be able to load small corpora, format text, apply the models through executing pieces of code, gradually discover the theoretical parts by possibly modifying the code or the parameters, and traverse theories and concrete problems through a constant interaction between the user and the machine. The data sizes and hardware requirements are kept to a reasonable minimum so that a user can see instantly, or at least quickly, the results of most experiments on most machines.The book does not assume a deep knowledge of Python, and an introduction to this language aimed at Text Processing is given in Ch. 2, which will enable the reader to touch all the programming concepts, including NumPy arrays and PyTorch tensors as fundamental structures to represent and process numerical data in Python, or Keras for training Neural Networks to classify texts. Covering topics like Word Segmentation and Part-of-Speech and Sequence Annotation, the textbook also gives an in-depth overview of Transformers (for instance, BERT), Self-Attention and Sequence-to-Sequence Architectures.

In this book the author's theoretical framework builds on linguistic and psychological research, arguing that similar image-schematic notions should be grouped together into interconnected family hierarchies, with complexity increasing with regard to the addition of spatial and conceptual primitives. She introduces an image schema logic as a language to model image schemas, and she shows how the semantic content of image schemas can be used to improve computational concept invention.The book will be of value to researchers in artificial intelligence, cognitive science, psychology, and creativity.

In this book the author's theoretical framework builds on linguistic and psychological research, arguing that similar image-schematic notions should be grouped together into interconnected family hierarchies, with complexity increasing with regard to the addition of spatial and conceptual primitives. She introduces an image schema logic as a language to model image schemas, and she shows how the semantic content of image schemas can be used to improve computational concept invention.The book will be of value to researchers in artificial intelligence, cognitive science, psychology, and creativity.

This book examines the contributions of the transhumanism approach to technology, in particular the contributed chapters are wary of the implications of this popular idea.The volume is organized into four parts concerning philosophical, military, technological and sociological aspects of transhumanism, but the reader is free to choose various reading patterns. Topics discussed include gene editing, the singularity, ethical machines, metaphors in AI, mind uploading, and the philosophy of art, and some perspectives taken or discussed examine transhumanism within the context of the philosophy of technology, transhumanism as a derailed anthropology, and critical sociological aspects that consider transhumanism in the context of topical concerns such as whiteness, maleness, and masculinity.The book will be of value to researchers engaged with artificial intelligence, and the ethical, societal, and philosophical impacts of science and technology.

This book examines the contributions of the transhumanism approach to technology, in particular the contributed chapters are wary of the implications of this popular idea.The volume is organized into four parts concerning philosophical, military, technological and sociological aspects of transhumanism, but the reader is free to choose various reading patterns. Topics discussed include gene editing, the singularity, ethical machines, metaphors in AI, mind uploading, and the philosophy of art, and some perspectives taken or discussed examine transhumanism within the context of the philosophy of technology, transhumanism as a derailed anthropology, and critical sociological aspects that consider transhumanism in the context of topical concerns such as whiteness, maleness, and masculinity.The book will be of value to researchers engaged with artificial intelligence, and the ethical, societal, and philosophical impacts of science and technology.

This open access book offers a comprehensive and thorough introduction to almost all aspects of metalearning and automated machine learning (AutoML), covering the basic concepts and architecture, evaluation, datasets, hyperparameter optimization, ensembles and workflows, and also how this knowledge can be used to select, combine, compose, adapt and configure both algorithms and models to yield faster and better solutions to data mining and data science problems. It can thus help developers to develop systems that can improve themselves through experience.As one of the fastest-growing areas of research in machine learning, metalearning studies principled methods to obtain efficient models and solutions by adapting machine learning and data mining processes. This adaptation usually exploits information from past experience on other tasks and the adaptive processes can involve machine learning approaches. As a related area to metalearning and a hot topic currently, AutoML is concerned with automating the machine learning processes. Metalearning and AutoML can help AI learn to control the application of different learning methods and acquire new solutions faster without unnecessary interventions from the user.This book is a substantial update of the first edition published in 2009. It includes 18 chapters, more than twice as much as the previous version. This enabled the authors to cover the most relevant topics in more depth and incorporate the overview of recent research in the respective area. The book will be of interest to researchers and graduate students in the areas of machine learning, data mining, data science and artificial intelligence.

This open access book provides an in-depth description of the EU project European Language Grid (ELG). Its motivation lies in the fact that Europe is a multilingual society with 24 official European Union Member State languages and dozens of additional languages including regional and minority languages. The only meaningful way to enable multilingualism and to benefit from this rich linguistic heritage is through Language Technologies (LT) including Natural Language Processing (NLP), Natural Language Understanding (NLU), Speech Technologies and language-centric Artificial Intelligence (AI) applications. The European Language Grid provides a single umbrella platform for the European LT community, including research and industry, effectively functioning as a virtual home, marketplace, showroom, and deployment centre for all services, tools, resources, products and organisations active in the field. Today the ELG cloud platform already offers access to more than 13,000 language processing tools and language resources. It enables all stakeholders to deposit, upload and deploy their technologies and datasets. The platform also supports the long-term objective of establishing digital language equality in Europe by 2030 – to create a situation in which all European languages enjoy equal technological support. This is the very first book dedicated to Language Technology and NLP platforms. Cloud technology has only recently matured enough to make the development of a platform like ELG feasible on a larger scale. The book comprehensively describes the results of the ELG project. Following an introduction, the content is divided into four main parts: (I) ELG Cloud Platform; (II) ELG Inventory of Technologies and Resources; (III) ELG Community and Initiative; and (IV) ELG Open Calls and Pilot Projects.

This open access book provides an in-depth description of the EU project European Language Grid (ELG). Its motivation lies in the fact that Europe is a multilingual society with 24 official European Union Member State languages and dozens of additional languages including regional and minority languages. The only meaningful way to enable multilingualism and to benefit from this rich linguistic heritage is through Language Technologies (LT) including Natural Language Processing (NLP), Natural Language Understanding (NLU), Speech Technologies and language-centric Artificial Intelligence (AI) applications. The European Language Grid provides a single umbrella platform for the European LT community, including research and industry, effectively functioning as a virtual home, marketplace, showroom, and deployment centre for all services, tools, resources, products and organisations active in the field. Today the ELG cloud platform already offers access to more than 13,000 language processing tools and language resources. It enables all stakeholders to deposit, upload and deploy their technologies and datasets. The platform also supports the long-term objective of establishing digital language equality in Europe by 2030 – to create a situation in which all European languages enjoy equal technological support. This is the very first book dedicated to Language Technology and NLP platforms. Cloud technology has only recently matured enough to make the development of a platform like ELG feasible on a larger scale. The book comprehensively describes the results of the ELG project. Following an introduction, the content is divided into four main parts: (I) ELG Cloud Platform; (II) ELG Inventory of Technologies and Resources; (III) ELG Community and Initiative; and (IV) ELG Open Calls and Pilot Projects.

This open access book presents a comprehensive collection of the European Language Equality (ELE) project’s results, its strategic agenda and roadmap with key recommendations to the European Union on how to achieve digital language equality in Europe by 2030. The fabric of the EU linguistic landscape comprises 24 official languages and over 60 regional and minority languages. However, language barriers still hamper communication and the free flow of information. Multilingualism is a key cultural cornerstone of Europe, signifying what it means to be and to feel European. Various studies and resolutions have found a striking imbalance in the support of Europe’s languages through technologies, issuing a call to action. Following an introduction, the book is divided into two parts. The first part describes the state of the art of language technology and language-centric AI and the definition and metrics developed to measure digital language equality. It also presents the status quo in 2022/2023, i.e., the current level of technology support for over 30 European languages. The second part describes plans and recommendations on how to bring about digital language equality in Europe by 2030. It includes chapters on the setup and results of the community consultation process, four technical deep dives, an overview of existing strategic documents and an abridged version of the strategic agenda and roadmap.The recommendations have been prepared jointly with the European community in the fields of language technology, natural language processing, and language-centric AI, as well as with representatives of relevant initiatives and associations, language communities and regional and minority language groups. Ensuring appropriate technology support for all European languages will not only create jobs, growth and opportunities in the digital single market. Overcoming language barriers in the digital environment is also essential for an inclusive society and for providing unity in diversity for many years to come.

This open access book presents a comprehensive collection of the European Language Equality (ELE) project’s results, its strategic agenda and roadmap with key recommendations to the European Union on how to achieve digital language equality in Europe by 2030. The fabric of the EU linguistic landscape comprises 24 official languages and over 60 regional and minority languages. However, language barriers still hamper communication and the free flow of information. Multilingualism is a key cultural cornerstone of Europe, signifying what it means to be and to feel European. Various studies and resolutions have found a striking imbalance in the support of Europe’s languages through technologies, issuing a call to action. Following an introduction, the book is divided into two parts. The first part describes the state of the art of language technology and language-centric AI and the definition and metrics developed to measure digital language equality. It also presents the status quo in 2022/2023, i.e., the current level of technology support for over 30 European languages. The second part describes plans and recommendations on how to bring about digital language equality in Europe by 2030. It includes chapters on the setup and results of the community consultation process, four technical deep dives, an overview of existing strategic documents and an abridged version of the strategic agenda and roadmap.The recommendations have been prepared jointly with the European community in the fields of language technology, natural language processing, and language-centric AI, as well as with representatives of relevant initiatives and associations, language communities and regional and minority language groups. Ensuring appropriate technology support for all European languages will not only create jobs, growth and opportunities in the digital single market. Overcoming language barriers in the digital environment is also essential for an inclusive society and for providing unity in diversity for many years to come.

This monograph explores the synergy of Artificial Intelligence (AI), Augmented Reality (AR) and cognitive processes to enhance spatial abilities — an integral aspect of cognitive development. The ability to comprehend and manipulate spatial information is not only fundamental to our understanding of the physical world but also plays a pivotal role in numerous academic and professional fields. Recognizing the profound impact of spatial ability on scientific disciplines and educational achievement, this monograph takes on the challenge of enhancing spatial skills among users.The authors present the design and development of a mobile training system that incorporates AR features to enhance learners’ spatial ability. Involving mental generation, transformation, and rotation of visual images for understanding spatial relationships, spatial ability is closely linked to success in various scientific disciplines and educational pursuits. While spatial visualization skills testsare available, this monograph takes a unique approach by focusing on developing targeted interventions to improve spatial ability. It aims to unlock new avenues for cognitive growth and dive into the untapped potential within the realm of spatial intelligence. Beyond its emphasis on spatial ability enhancement, this monograph goes above and beyond traditional approaches by integrating AI techniques into the training system. As such, it aims to provide personalized and adaptive learning experiences for learners. The training system, through intelligent techniques, dynamically analyzes individual learners’ strengths, weaknesses, and progress, tailoring content and challenges to their specific needs. This effort establishes a new frontier in educational technology, offering a groundbreaking solution that not only augments spatial ability development but also showcases the transformative potential of AI in reshaping the learning experience.The book is a valuable resource for researchers, educators, developers and technology enthusiasts, as it exemplifies the profound impact of AI and AR in shaping the future of online learning experiences.

This monograph explores the synergy of Artificial Intelligence (AI), Augmented Reality (AR) and cognitive processes to enhance spatial abilities — an integral aspect of cognitive development. The ability to comprehend and manipulate spatial information is not only fundamental to our understanding of the physical world but also plays a pivotal role in numerous academic and professional fields. Recognizing the profound impact of spatial ability on scientific disciplines and educational achievement, this monograph takes on the challenge of enhancing spatial skills among users.The authors present the design and development of a mobile training system that incorporates AR features to enhance learners’ spatial ability. Involving mental generation, transformation, and rotation of visual images for understanding spatial relationships, spatial ability is closely linked to success in various scientific disciplines and educational pursuits. While spatial visualization skills testsare available, this monograph takes a unique approach by focusing on developing targeted interventions to improve spatial ability. It aims to unlock new avenues for cognitive growth and dive into the untapped potential within the realm of spatial intelligence. Beyond its emphasis on spatial ability enhancement, this monograph goes above and beyond traditional approaches by integrating AI techniques into the training system. As such, it aims to provide personalized and adaptive learning experiences for learners. The training system, through intelligent techniques, dynamically analyzes individual learners’ strengths, weaknesses, and progress, tailoring content and challenges to their specific needs. This effort establishes a new frontier in educational technology, offering a groundbreaking solution that not only augments spatial ability development but also showcases the transformative potential of AI in reshaping the learning experience.The book is a valuable resource for researchers, educators, developers and technology enthusiasts, as it exemplifies the profound impact of AI and AR in shaping the future of online learning experiences.

Since the last edition of this book (2014), progress has been astonishing in all areas of Natural Language Processing, with recent achievements in Text Generation that spurred a media interest going beyond the traditional academic circles. Text Processing has meanwhile become a mainstream industrial tool that is used, to various extents, by countless companies. As such, a revision of this book was deemed necessary to catch up with the recent breakthroughs, and the author discusses models and architectures that have been instrumental in the recent progress of Natural Language Processing.As in the first two editions, the intention is to expose the reader to the theories used in Natural Language Processing, and to programming examples that are essential for a deep understanding of the concepts. Although present in the previous two editions, Machine Learning is now even more pregnant, having replaced many of the earlier techniques to process text. Many new techniques build on the availability of text. Using Python notebooks, the reader will be able to load small corpora, format text, apply the models through executing pieces of code, gradually discover the theoretical parts by possibly modifying the code or the parameters, and traverse theories and concrete problems through a constant interaction between the user and the machine. The data sizes and hardware requirements are kept to a reasonable minimum so that a user can see instantly, or at least quickly, the results of most experiments on most machines.The book does not assume a deep knowledge of Python, and an introduction to this language aimed at Text Processing is given in Ch. 2, which will enable the reader to touch all the programming concepts, including NumPy arrays and PyTorch tensors as fundamental structures to represent and process numerical data in Python, or Keras for training Neural Networks to classify texts. Covering topics like Word Segmentation and Part-of-Speech and Sequence Annotation, the textbook also gives an in-depth overview of Transformers (for instance, BERT), Self-Attention and Sequence-to-Sequence Architectures.

This open access book presents the concept of Informed Machine Learning and demonstrates its practical use with a compelling collection of applications of this paradigm in industrial and business use cases. These range from health care over manufacturing and material science to more advanced combinations with deep learning, say, in the form of physical informed neural networks. The book is intended for those interested in modern informed machine learning for a wide range of practical applications where the aspect of small data sets is a challenge.Machine Learning with small amounts of data? After the recent success of Artificial Intelligence based on training with massive amounts of data, this idea may sound exotic. However, it addresses crucial needs of practitioners in industry. While many industrial applications stand to benefit from the use of AI, the amounts of data needed by current learning paradigms are often hard to come by in industrial settings. As an alternative, learning methods and models are called for which integrate other sources of knowledge in order to compensate for the lack of data. This is where the principle of “Informed Machine Learning” comes into play.Informed Machine Learning combines purely data driven learning and knowledge-based techniques to learn from both data and knowledge. This has several advantages. It reduces the need for data, it often results in smaller, less complex and more robust models, and even makes machine learning applicable in settings where data is scarce. The kind of knowledge to be incorporated into learning processes can take many different forms, for example, differential equations, analytical models, simulation results, logical rules, knowledge graphs, or human feedback which makes the approach overall very powerful and widely applicable.

This open access book presents the concept of Informed Machine Learning and demonstrates its practical use with a compelling collection of applications of this paradigm in industrial and business use cases. These range from health care over manufacturing and material science to more advanced combinations with deep learning, say, in the form of physical informed neural networks. The book is intended for those interested in modern informed machine learning for a wide range of practical applications where the aspect of small data sets is a challenge.Machine Learning with small amounts of data? After the recent success of Artificial Intelligence based on training with massive amounts of data, this idea may sound exotic. However, it addresses crucial needs of practitioners in industry. While many industrial applications stand to benefit from the use of AI, the amounts of data needed by current learning paradigms are often hard to come by in industrial settings. As an alternative, learning methods and models are called for which integrate other sources of knowledge in order to compensate for the lack of data. This is where the principle of “Informed Machine Learning” comes into play.Informed Machine Learning combines purely data driven learning and knowledge-based techniques to learn from both data and knowledge. This has several advantages. It reduces the need for data, it often results in smaller, less complex and more robust models, and even makes machine learning applicable in settings where data is scarce. The kind of knowledge to be incorporated into learning processes can take many different forms, for example, differential equations, analytical models, simulation results, logical rules, knowledge graphs, or human feedback which makes the approach overall very powerful and widely applicable.

This book presents all components and knowledge sources required for Transparent Information Retrieval. Depending on the respective topic and taking care of their interoperability, both deep and shallow technology is used. The processing starts from the analysis of the text data and collects its results in a multilingual conceptual network, this way enabling Transparent Information Retrieval where users communicate with the system in their native language while the documents could be in a different language, transparent to the users. To do so, the author investigates all text analysis components required for multilingual indexing, starting from preparatory work like language and topic identification, continuing with sentence splitting and tokenization (including Chinese), and describing lexical analysis, also for multiword entries and Named Entities. Entries are then disambiguated both on syntactic (by a tagger) and semantic level (by multilingual word sense disambiguation). The analysis results are collected in a dynamic multilingual ConceptNet, which is an index structure extended by monolingual relations (like synonyms, or head-modifier links) as well as multilingual ones (translations). In addition to many European languages also Turkish, Arabic, Persian, and Chinese are treated. The book concludes with a description of components needed to build the required resources, like crawlers, bilingual term extraction, and tools for defaulting linguistic annotations. For each component, readers will find a technology overview, a discussion of its main challenges in computational treatment, a description of the technical solution selected, and evaluation information.

This book is an essential guide for anyone interested in how artificial intelligence can enhance the quality of life for individuals who wish to maintain autonomy in their own homes. The author begins by introducing the reader to AI applications in independent living environments, such as smart assisted homes and AI-driven personalization, and thoughtfully explores the ethical challenges involved. With a strong focus on the intersection of technology and human needs, the book provides a detailed roadmap for building intelligent systems that promote safety, independence, and dignity, especially for elderly or vulnerable populations. The author offers both foundational knowledge and critical discussions around the opportunities and limitations of AI when applied to daily life scenarios.A major strength of the book lies in its thorough examination of multimodal systems. Readers are introduced to a rich array of sensor technologies including wearable devices, environmental sensors, vision-based systems, and sound-based inputs. These components are described not only in terms of their individual functionalities but also in how they interact and fuse data to support complex inference tasks. The text walks the reader through system architectures—centralized and distributed—while emphasizing data fusion, synchronization, and real-time versus batch processing. Through practical examples such as fall detection alerts and activity recognition, the book highlights the engineering challenges and solutions involved in building robust, responsive, and user-accepted assistive systems. Ethical deployment, user engagement, long-term maintenance, and family involvement are all addressed in ways that reflect real-world concerns and user diversity.The book also tackles some of the most pressing topics in AI today: data privacy, explainability, and trust. With an entire section dedicated to synthetic data, it explains how artificial data can be used to train effective models while safeguarding user privacy.

This book is an essential guide for anyone interested in how artificial intelligence can enhance the quality of life for individuals who wish to maintain autonomy in their own homes. The author begins by introducing the reader to AI applications in independent living environments, such as smart assisted homes and AI-driven personalization, and thoughtfully explores the ethical challenges involved. With a strong focus on the intersection of technology and human needs, the book provides a detailed roadmap for building intelligent systems that promote safety, independence, and dignity, especially for elderly or vulnerable populations. The author offers both foundational knowledge and critical discussions around the opportunities and limitations of AI when applied to daily life scenarios.A major strength of the book lies in its thorough examination of multimodal systems. Readers are introduced to a rich array of sensor technologies including wearable devices, environmental sensors, vision-based systems, and sound-based inputs. These components are described not only in terms of their individual functionalities but also in how they interact and fuse data to support complex inference tasks. The text walks the reader through system architectures—centralized and distributed—while emphasizing data fusion, synchronization, and real-time versus batch processing. Through practical examples such as fall detection alerts and activity recognition, the book highlights the engineering challenges and solutions involved in building robust, responsive, and user-accepted assistive systems. Ethical deployment, user engagement, long-term maintenance, and family involvement are all addressed in ways that reflect real-world concerns and user diversity.The book also tackles some of the most pressing topics in AI today: data privacy, explainability, and trust. With an entire section dedicated to synthetic data, it explains how artificial data can be used to train effective models while safeguarding user privacy.

This open access book is meant as a textbook for Computer Science students who are looking for a gentle introduction to the world of quantum computing. More specifically, it is written for readers who have basic knowledge of Artificial Intelligence (AI) and Machine Learning (ML) and have a certain familiarity with search algorithms, optimization techniques, and neural networks. This is not because the authors are interested in Quantum AI or Quantum ML, but because they start from the basic premise that there exists a conceptual bridge between certain AI/ML models and certain quantum computing models. The purpose of this book is therefore 1) to revisit these AI/ML models and their applications, and 2) to build on this familiar foundation to segue into the study of quantum computing and its possible use cases. The presentation is technical but pragmatic and practice oriented. The authors cover theory to the necessary extent but largely proceed in an example-driven manner. Most of the examples are concerned with combinatorial optimization and consider problems that can be cast as quadratic unconstrained binary optimization problems.Numerous python/numpy/scipy codes support the mathematical discussion and demonstrate how to put theory into practice, accompanied by exercises for each chapter. Parts of the material were adopted from long running lectures on pattern recognition, on the foundations of quantum computing, and on quantum computing algorithms, which are taught by the authors in the Computer Science master’s program at the University of Bonn.

Machine learning is one of the leading areas of artificial intelligence. It concerns the study and development of quantitative models that enable a computer to carry out operations without having been expressly programmed to do so.In this situation, learning is about identifying complex shapes and making intelligent decisions. The challenge in completing this task, given all the available inputs, is that the set of potential decisions is typically quite difficult to enumerate. Machine learning algorithms have been developed with the goal of learning about the problem to be handled based on a collection of limited data from this problem in order to get around this challenge.This textbook presents the scientific foundations of supervised learning theory, the most widespread algorithms developed according to this framework, as well as the semi-supervised and the learning-to-rank frameworks, at a level accessible to master's students. The aim of the book is to provide a coherent presentation linking the theory to the algorithms developed in this field. In addition, this study is not limited to the presentation of these foundations, but it also presents exercises, and is intended for readers who seek to understand the functioning of these models sometimes designated as black boxes.

The field of Artificial Intelligence has seen explosive growth in recent years, yet a persistent challenge remains, namely bridging the gap between theoretical concepts and practical implementation. Too often, students encounter either highly abstract mathematical treatments disconnected from real-world applications, or simplified implementations that fail to convey the underlying principles. This textbook directly addresses this challenge through its unique approach combining clear theoretical explanations with comprehensive Python implementations. Drawing from the author’s extensive experience teaching at the University of eCampus, Italy, this book provides a thorough exploration of intelligent systems, covering classical approaches to cutting-edge techniques. Organized into three main areas, the book explores the foundations of intelligent systems, examines optimization and search methods that form the backbone of AI solutions, and ends by investigating machine learning fundamentals that enable systems to derive knowledge from experience. A distinguishing feature of this work is its practical approach. Each theoretical concept is paired with Python implementations and exercises. This hands-on methodology develops both conceptual understanding and practical skills simultaneously. The exercises progress from basic implementations to complex real-world problems.The textbook aims to serve both undergraduate and graduate students in computer science, engineering, and related disciplines. It assumes basic programming knowledge but introduces concepts progressively. Professionals implementing intelligent systems will also find valuable insights and practical guidance. Despite AI’s rapid evolution, this book provides both current knowledge and the conceptual framework necessary for understanding future developments. Ethical considerations are addressed throughout, encouraging critical thinking about responsible AI implementation. It is the author’s hope that this book will be a valuable resource in the reader’s journey to understand and design intelligent systems.

The author provides a rigorous, technically grounded framework for analysing, modelling, and mitigating adversarial threats against artificial intelligence systems. The book focuses on adversarial machine learning and AI-native cyber-attacks, examining how threat actors exploit vulnerabilities in data pipelines, model architectures, training procedures, and inference mechanisms to compromise the integrity, confidentiality, and availability of AI-driven systems.The significance of this book lies in addressing a structural gap in contemporary cybersecurity practice. Traditional security models were designed for deterministic software and networked systems, not for probabilistic, adaptive, and data-driven AI models. As AI increasingly underpins high-stakes decision-making across finance, healthcare, critical infrastructure, autonomous systems, and defence, adversarial manipulation of AI models has become an operational and strategic risk rather than a theoretical concern. This book responds directly to that risk by reframing cybersecurity through a model-centric, adversarial lens.The book is organised around the primary classes of AI cyber-attacks, each chapter analysing a major attack class that subsumes multiple concrete adversarial techniques. Collectively, these chapters cover the most dangerous and operationally relevant attack vectors observed in real-world AI deployments, including adversarial perturbations, data poisoning and backdoors, model extraction and inversion, membership inference, prompt injection and jailbreak attacks on large language models, AI-powered social engineering and deepfakes, federated learning and reinforcement learning attacks, and adversarial malware targeting AI-based security systems. Key features include lifecycle-based threat modelling, red-teaming methodologies, quantitative risk assessment frameworks, and technical countermeasures such as adversarial training, differential privacy, secure aggregation, cryptographic watermarking, and AI-specific governance controls.Readers will gain an operational understanding of how AI systems fail under adversarial pressure, how to simulate and test adversarial behaviours, and how to design resilient AI architectures suitable for deployment in high-risk environments. The book assumes prior familiarity with machine learning fundamentals and cybersecurity concepts and is aimed at advanced practitioners, researchers, and postgraduate audiences.

The Internet of Services and the Internet of Things are major building blocks of the Future Internet. The digital enterprise of the future is based not only on mobile, social, and cloud technologies, but also on se­mantic technologies and the future Internet of Everything. Semantic technologies now enable mass cus­tomization for the delivery of goods and services that meet individual customer needs and tastes with near mass production efficiency and reliability. This is creating a competitive advantage in the industrial econ­omy, the service economy, and the emerging data economy, leading to smart products, smart services, and smart data, all adaptable to specific tasks, locations, situations, and contexts of smart spaces. Such tech­nologies allow us to describe, revise, and adapt the characteristics, functions, processes, and usage patterns of customization targets on the basis of machine-understandable content representation that enables auto­mated processing and information sharing between human and software agents. This book explains the principal achievements of the Theseus research program, one of the central pro­grams in the German government's Digital 2015 initiative and its High-Tech Strategy 2020. The methods, toolsets, and standards for semantic technologies developed during this program form a solid basis for the fourth industrial revolution (Industrie 4.0), the hybrid service economy, and the transformation of big data into useful smart data for the emerging data economy. The contributing authors are leading scientists and engineers,representing world-class academic and in­dustrial research teams, and the ideas, technologies, and representative use cases they describe in the book derive from results in multidisciplinary fields, such as the Internet of Services; the Semantic Web, and semantic technologies, knowledge management, and search; user interfaces, multimodal interaction, and visualization; machine learning and data mining; and business process support, manufacturing, automa­tion, medical systems, and integrated service engineering. The book will be of value to both researchers and practitioners in these domains.

This book will help researchers and engineers in the design of ethical systems for robots, addressing the philosophical questions that arise and exploring modern applications such as assistive robots and self-driving cars.The contributing authors are among the leading academic and industrial researchers on this topic and the book will be of value to researchers, graduate students and practitioners engaged with robot design, artificial intelligence and ethics.

The Internet of Services and the Internet of Things are major building blocks of the Future Internet. The digital enterprise of the future is based not only on mobile, social, and cloud technologies, but also on se­mantic technologies and the future Internet of Everything. Semantic technologies now enable mass cus­tomization for the delivery of goods and services that meet individual customer needs and tastes with near mass production efficiency and reliability. This is creating a competitive advantage in the industrial econ­omy, the service economy, and the emerging data economy, leading to smart products, smart services, and smart data, all adaptable to specific tasks, locations, situations, and contexts of smart spaces. Such tech­nologies allow us to describe, revise, and adapt the characteristics, functions, processes, and usage patterns of customization targets on the basis of machine-understandable content representation that enables auto­mated processing and information sharing between human and software agents. This book explains the principal achievements of the Theseus research program, one of the central pro­grams in the German government's Digital 2015 initiative and its High-Tech Strategy 2020. The methods, toolsets, and standards for semantic technologies developed during this program form a solid basis for the fourth industrial revolution (Industrie 4.0), the hybrid service economy, and the transformation of big data into useful smart data for the emerging data economy. The contributing authors are leading scientists and engineers,representing world-class academic and in­dustrial research teams, and the ideas, technologies, and representative use cases they describe in the book derive from results in multidisciplinary fields, such as the Internet of Services; the Semantic Web, and semantic technologies, knowledge management, and search; user interfaces, multimodal interaction, and visualization; machine learning and data mining; and business process support, manufacturing, automa­tion, medical systems, and integrated service engineering. The book will be of value to both researchers and practitioners in these domains.

Future technical systems will be companion systems, competent assistants that provide their functionality in a completely individualized way, adapting to a user’s capabilities, preferences, requirements, and current needs, and taking into account both the emotional state and the situation of the individual user.This book presents the enabling technology for such systems. It introduces a variety of methods and techniques to implement an individualized, adaptive, flexible, and robust behavior for technical systems by means of cognitive processes, including perception, cognition, interaction, planning, and reasoning. The technological developments are complemented by empirical studies from psychological and neurobiological perspectives.

This book will help researchers and engineers in the design of ethical systems for robots, addressing the philosophical questions that arise and exploring modern applications such as assistive robots and self-driving cars.The contributing authors are among the leading academic and industrial researchers on this topic and the book will be of value to researchers, graduate students and practitioners engaged with robot design, artificial intelligence and ethics.

Future technical systems will be companion systems, competent assistants that provide their functionality in a completely individualized way, adapting to a user’s capabilities, preferences, requirements, and current needs, and taking into account both the emotional state and the situation of the individual user.This book presents the enabling technology for such systems. It introduces a variety of methods and techniques to implement an individualized, adaptive, flexible, and robust behavior for technical systems by means of cognitive processes, including perception, cognition, interaction, planning, and reasoning. The technological developments are complemented by empirical studies from psychological and neurobiological perspectives.

Life-like characters is one of the most exciting technologies for human-computer interface applications today. They convincingly take the roles of virtual presenters, synthetic actors and sales personas, teammates and tutors. A common characteristic underlying their life-likeness or believability as virtual conversational partners is computational models that provide them with affective functions such as synthetic emotions and personalities and implement human interactive behavior. The wide dissemination of life-like characters in multimedia systems, however, will greatly depend on the availability of control languages and tools that facilitate scripting of intelligent conversational behaviour. This book presents the first comprehensive collection of the latest developments in scripting and representation languages for life-like characters, rounded off with an in-depth comparison and synopsis of the major approaches. Introducing toolkits for authoring animated characters further supports the ease of use of this new interface technology. Life-like characters being a vibrant research area, various applications have been designed and implemented. This book offers coverage of the most successful and promising applications, ranging from product presentation and student training to knowledge integration and interactive gaming. It also discusses the key challenges in the area and provides design guidelines for employing life-like characters.