Machine learning

This book is devoted to the emerging field of integrated visual knowledge discovery that combines advances in artificial intelligence/machine learning and visualization/visual analytic. A long-standing challenge of artificial intelligence (AI) and machine learning (ML) is explaining models to humans, especially for live-critical applications like health care. A model explanation is fundamentally human activity, not only an algorithmic one. As current deep learning studies demonstrate, it makes the paradigm based on the visual methods critically important to address this challenge. In general, visual approaches are critical for discovering explainable high-dimensional patterns in all types in high-dimensional data offering "e;n-D glasses,"e; where preserving high-dimensional data properties and relations in visualizations is a major challenge. The current progress opens a fantastic opportunity in this domain. This book is a collection of 25 extended works of over 70 scholars presented at AI and visual analytics related symposia at the recent International Information Visualization Conferences with the goal of moving this integration to the next level.  The sections of this book cover integrated systems, supervised learning, unsupervised learning, optimization, and evaluation of visualizations. The intended audience for this collection includes those developing and using emerging AI/machine learning and visualization methods. Scientists, practitioners, and students can find multiple examples of the current integration of AI/machine learning and visualization for visual knowledge discovery. The book provides a vision of future directions in this domain. New researchers will find here an inspiration to join the profession and to be involved for further development. Instructors in AI/ML and visualization classes can use it as a supplementary source in their undergraduate and graduate classes.

This edited volume on machine learning and big data analytics (Proceedings of ICMLBDA 2022) is intended to be used as a reference book for researchers and professionals to share their research and reports of new technologies and applications in Machine Learning and Big Data Analytics like biometric Recognition Systems, medical diagnosis, industries, telecommunications, AI Petri Nets Model-Based Diagnosis, gaming, stock trading, Intelligent Aerospace Systems, robot control, law, remote sensing and scientific discovery agents and multiagent systems; and natural language and Web intelligence.The intent of this book is to provide awareness of algorithms used for machine learning and big data in the advanced Scientific Technologies, provide a correlation of multidisciplinary areas and become a point of great interest for Data Scientists, systems architects, developers, new researchers and graduate level students. This volume provides cutting-edge research from around the globeon this field. Current status, trends, future directions, opportunities, etc. are discussed, making it friendly for beginners and young researchers.

This book collects different methodologies that permit metaheuristics and machine learning to solve real-world problems. This book has exciting chapters that employ evolutionary and swarm optimization tools combined with machine learning techniques. The fields of applications are from distribution systems until medical diagnosis, and they are also included different surveys and literature reviews that will enrich the reader. Besides, cutting-edge methods such as neuroevolutionary and IoT implementations are presented in some chapters. In this sense, the book provides theory and practical content with novel machine learning and metaheuristic algorithms. The chapters were compiled using a scientific perspective. Accordingly, the book is primarily intended for undergraduate and postgraduate students of Science, Engineering, and Computational Mathematics and can be used in courses on Artificial Intelligence, Advanced Machine Learning, among others. Likewise, the material can be helpful for research from the evolutionary computation, artificial intelligence communities. 

This book provides a novel framework for understanding and revising labor markets and education policies in an era of machine learning. It posits that while learning and knowing both require thinking, learning is fundamentally different than knowing because it results in cognitive processes that change over time. Learning, in contrast to knowing, requires time and agency. Therefore, ¿learning algorithms¿¿that enable machines to modify their actions based on real-world experiences¿are a fundamentally new form of artificial intelligence that have potential to be even more disruptive to labor markets than prior introductions of digital technology. To explore the difference between knowing and learning, Turing¿s ¿Imitation Game,¿¿that he proposed as a test for machine thinking¿is expanded to include time dependence. The arguments presented in the book introduce three novel concepts: (1) Comparative learning advantage: This is a concept analogous to comparative labor advantagebut arises from the disparate times required to learn new knowledge bases/skillsets. It is argued that in the future, comparative learning advantages between humans and machines will determine their division of labor. (2) Two dimensions of job performance¿expertise and interpersonal: Job tasks can be sorted into two broad categories. Tasks that require expertise have stable endpoints, which makes these tasks inherently repetitive and subject to automation. Tasks that are interpersonal are highly context-dependent and lack stable endpoints, which makes these tasks inherently non-routine. Humans compared to machines have a comparative learning advantage along the interpersonal dimension, which is increasing in value economically. (3) The Learning Game is a time-dependent version of Turing¿s ¿Imitation Game.¿ It is more than a thought experiment. The ¿Learning Game¿ provides a mathematical framework with quantitative criteria for training and assessing comparative learningadvantages. The book is highly interdisciplinary¿presenting philosophical arguments in economics, artificial intelligence, and education. It also provides data, mathematical analysis, and testable criteria that researchers in these fields will find of practical use. The book calls for a rethinking of how labor markets operate and how the education system should prepare students for future jobs. It concludes with a list of counterintuitive recommendations for future education and labor policies that all stakeholders¿employers, employees, educators, students, and political leaders¿should heed.

Machine Learning and Noisy Labels: Definitions, Theory, Techniques and Solutions provides an ideal introduction to machine learning with noisy labels that is suitable for senior undergraduates, post graduate students, researchers and practitioners using, and researching, machine learning methods. Most of the modern machine learning models based on deep learning techniques depend on carefully curated and cleanly labeled training sets to be reliably trained and deployed. However, the expensive labeling process involved in the acquisition of such training sets limits the number and size of datasets available to build new models, slowing down progress in the field. This book defines the different types of label noise, introduces the theory behind the problem, presents the main techniques that enable the effective use of noisy-label training sets, and explains the most accurate methods.

Many-Sorted Algebras for Deep Learning and Quantum Technology presents a precise and rigorousdescription of basic concepts in quantum technologies and how they relate to deep learning and quantum theory. Current merging of quantum theory and deep learning techniques provides the need for a source that gives readers insights into the algebraic underpinnings of these disciplines. Although analytical, topological, probabilistic, as well as geometrical concepts are employed in many of these areas, algebra exhibits the principal thread; hence, this thread is exposed using many-sorted algebras. This book includes hundreds of well-designed examples that illustrate the intriguing concepts in quantum systems. Along with these examples are numerous visual displays. In particular, the polyadic graph shows the types or sorts of objects used in quantum or deep learning. It also illustrates all the inter and intra-sort operations needed in describing algebras. In brief, it provides the closure conditions. Throughout the book, all laws or equational identities needed in specifying an algebraic structure are precisely described.

This book constitutes two challenges that were held in conjunction with the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2022, which took place in Singapore during September 18-22, 2022. The peer-reviewed 20 long and 5 short papers included in this volume stem from the following three biomedical image analysis challenges: Mitosis Domain Generalization Challenge (MIDOG 2022), Diabetic Retinopathy Analysis Challenge (CRAC 2022)The challenges share the need for developing and fairly evaluating algorithms that increase accuracy, reproducibility and efficiency of automated image analysis in clinically relevant applications.

Artificial neuronal networks open up radical new pathways for image creation. On the basis of textual prompts, machine-learning algorithms like Midjourney and DALL-E generate imagery that is simultaneously familiar and alien. Graphic designer Floyd Schulze uses this rapidly developing technology to recreate architectural icons. In an accompanying essay, Georg Vrachliotis takes up the topic on the theoretical level. OK Computer is the first book to deal with AI-generated architectural imagery from an artistic perspective.

This book constitutes the proceedings of the 17th International Conference on Research Challenges in Information Sciences, RCIS 2023, which took place in Corfu, Greece, during May 23¿26, 2023. It focused on the special theme "Information Science and the Connected World".The scope of RCIS is summarized by the thematic areas of information systems and their engineering; user-oriented approaches; data and information management; business process management; domain-specific information systems engineering; data science; information infrastructures, and reflective research and practice.The 28 full papers presented in this volume were carefully reviewed and selected from a total of 87 submissions. The book also includes 15 Forum papers and 6 Doctoral Consortium papers. The contributions were organized in topical sections named: Requirements; conceptual modeling and ontologies; machine learning and analytics; conceptual modeling and semantic networks; business process design and computing in the continuum; requirements and evaluation; monitoring and recommending; business process analysis and improvement; user interface and experience; forum papers; doctoral consortium papers. Two-page abstracts of the tutorials can be found in the back matter of the volume.

There are several popular books published in Healthcare Computational Informatics like Computational Bioengineering and Bioinformatics (2020), Springer; Health Informatics (2017), Springer; Health Informatics Vision: From Data via Information to Knowledge (2019), IOS Press; Data Analytics in Biomedical Engineering and Healthcare (2020), Elsevier. However, in all these mentioned books, the challenges in Biomedical Imaging are solved in one dimension by use of any specific technology like Image Processing, Machine Learning or Computer Aided Systems.  In this book, the book it has been attempted to bring all technologies related to computational analytics together and apply them on Biomedical Imaging.

This edited book provides information on emerging fields of next-generation healthcare informatics with a special emphasis on emerging developments and applications of artificial intelligence, deep learning techniques, computational intelligence methods, Internet of medical things (IoMT), optimization techniques, decision making, nanomedicine, and cloud computing. The book provides a conceptual framework and roadmap for decision-makers for this transformation. The chapters involved in this book cover challenges and opportunities for diabetic retinopathy detection based on deep learning applications, deep learning accelerators in IoT and IoMT, health data analysis, deep reinforcement-based conversational AI agent in healthcare systems, examination of health data performance, multisource data in intelligent medicine, application of genetic algorithms in health care, mental disorder, digital healthcare system with big data analytics, encryption methods in healthcare data security, computation and cognitive bias in healthcare intelligence and pharmacogenomics, guided imagery therapy, cancer detection and prediction techniques, medical image processing for coronavirus, and imbalance learning in health care.

This book presents recent improvements in peridynamic modeling of structures. It provides sufficient theory and numerical implementation helpful to both new and existing researchers in the field.  The main focus of the book is on the non-ordinary state-based (NOSB) peridynamics (PD) and its applications for performing finite deformation. It presents the framework for modeling high stretch polymers, viscoelastic materials, thermoelasticity, plasticity, and creep. It provides a systematic derivation for dimensionally reduced structures such as axisymmetric structures and beams. Also, it presents a novel approach to impose boundary conditions without suffering from displacement kinks near the boundary. Furthermore, it presents refinements to bond-based PD model by including rotation kinematics for modeling isotropic and composite materials. Moreover, it presents a PD - FEM coupling framework in ANSYS based on principle for virtual work. Lastly, it presents an application of neural networks in the peridynamic (PINN) framework. Sample codes are provided for readers to develop hands-on experience on peridynamic modeling.  Describes new developments in peridynamics and their applications in the presence of material and geometric nonlinearity; Describes an approach to seamlessly couple PD with FE; Introduces the use of the neural network in the PD framework to solve engineering problems;Provides theory and numerical examples for researchers and students to self-study and apply in their research (Codes are provided as supplementary material);Provides theoretical development and numerical examples suitable for graduate courses.

This book features high-quality research papers presented at the First Doctoral Symposium on Human Centered Computing (HUMAN 2023), jointly organized by Computer Society of India, Kolkata Chapter and Techno India University, West Bengal, on February 25, 2023. This book discusses the topics of modern human centered computing and its applications. The book showcases the fusion of human sciences (social and cognitive) with computer science (human¿computer interaction, signal processing, machine learning, and ubiquitous computing).

This book stems from the growing use of learning-based techniques, such as reinforcement learning and adaptive control, in the control of autonomous and safety-critical systems. Safety is critical to many applications, such as autonomous driving, air traffic control, and robotics. As these learning-enabled technologies become more prevalent in the control of autonomous systems, it becomes increasingly important to ensure that such systems are safe. To address these challenges, the authors provide a self-contained treatment of learning-based control techniques with rigorous guarantees of stability and safety. This book contains recent results on provably correct control techniques from specifications that go beyond safety and stability, such as temporal logic formulas. The authors bring together control theory, optimization, machine learning, and formal methods and present worked-out examples and extensive simulation examples to complement the mathematical style of presentation. Prerequisites are minimal, and the underlying ideas are accessible to readers with only a brief background in control-theoretic ideas, such as Lyapunov stability theory.

This book presents the concept of Control Barrier Function (CBF), which captures the evolution of safety requirements during the execution of a system and can be used to enforce safety. Safety is formalized using an emerging state-of-the-art approach based on CBFs, and many illustrative examples from autonomous driving, traffic control, and robot control are provided. Safety is central to autonomous systems since they are intended to operate with minimal or no human supervision, and a single failure could result in catastrophic results. The authors discuss how safety can be guaranteed via both theoretical and application perspectives. This presented method is computationally efficient and can be easily implemented in real-time systems that require high-frequency reactive control. In addition, the CBF approach can easily deal with nonlinear models and complex constraints used in a wide spectrum of applications, including autonomous driving, robotics, and traffic control. Withthe proliferation of autonomous systems, such as self-driving cars, mobile robots, and unmanned air vehicles, safety plays a crucial role in ensuring their widespread adoption. This book considers the integration of safety guarantees into the operation of such systems including typical safety requirements that involve collision avoidance, technological system limitations, and bounds on real-time executions. Adaptive approaches for safety are also proposed for time-varying execution bounds and noisy dynamics.

Microbial ecosystems are complex, with hundreds of members interacting with each other and the environment. The intricate and hidden behaviors underlying these interactions make research questions challenging - but can be better understood through machine learning. However, most machine learning that is used in microbiome work is a black box form of investigation, where accurate predictions can be made, but the inner logic behind what is driving prediction is hidden behind nontransparent layers of complexity

This second edition textbook covers a coherently organized framework for text analytics, which integrates material drawn from the intersecting topics of information retrieval, machine learning, and natural language processing. Particular importance is placed on deep learning methods. The chapters of this book span three broad categories:1. Basic algorithms: Chapters 1 through 7 discuss the classical algorithms for text analytics such as preprocessing, similarity computation, topic modeling, matrix factorization, clustering, classification, regression, and ensemble analysis.2. Domain-sensitive learning and information retrieval: Chapters 8 and 9 discuss learning models in heterogeneous settings such as a combination of text with multimedia or Web links. The problem of information retrieval and Web search is also discussed in the context of its relationship with ranking and machine learning methods. 3. Natural language processing: Chapters 10 through 16 discuss various sequence-centric and natural language applications, such as feature engineering, neural language models, deep learning, transformers, pre-trained language models, text summarization, information extraction, knowledge graphs, question answering, opinion mining, text segmentation, and event detection. Compared to the first edition, this second edition textbook (which targets mostly advanced level students majoring in computer science and math) has substantially more material on deep learning and natural language processing. Significant focus is placed on topics like transformers, pre-trained language models, knowledge graphs, and question answering.

This book is a collection of best selected research papers presented at 7th International Conference on Computing in Engineering and Technology (ICCET 2022), organized by Dr. Babasaheb Ambedkar Technological University, Lonere, India, during February 12 ¿ 13, 2022. Focusing on frontier topics and next-generation technologies, it presents original and innovative research from academics, scientists, students, and engineers alike. The theme of the conference is Applied Information Processing System.

Automation tools like machine learning are a necessity in our big data world. Thanks to the Internet and advancements in all facets of computer and storage technology, almost everyone has a voice in the Internet connected world. However, there are still very real physical limits in our physical world. This dichotomy-the seemingly limitless nature of technology enabled data colliding with the physical limits of the real world-has made automation tools a necessity, and predictive models powered by machine learning algorithms are one such tool.

This book constitutes the proceedings of the 9th International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2023, which took place in Santa Margherita di Pula, Italy, in May 2023. The 57 papers presented in this volume were carefully reviewed and selected from 72 submissions. They were organized in topical sections as follows: Inverse Problems in Imaging; Machine and Deep Learning in Imaging; Optimization for Imaging: Theory and Methods; Scale Space, PDEs, Flow, Motion and Registration.

Ihr Unternehmen hat sich für KI entschieden. Glückwunsch, was nun? Dieses praktische Buch bietet einen ganzheitlichen Plan für die Implementierung von KI aus der Perspektive der IT und des IT-Betriebs im Unternehmen. Sie erfahren etwas über die Fähigkeiten, das Potenzial, die Grenzen und die Herausforderungen von KI. In diesem Buch erfahren Sie, welche Rolle KI im Kontext etablierter Bereiche wie Design Thinking und DevOps, Governance und Change Management, Blockchain und Quantum Computing spielt, und diskutieren die Konvergenz von KI in diesen Schlüsselbereichen des Unternehmens.Deploying AI in the Enterprise bietet Anleitungen und Methoden zur effektiven Bereitstellung und Operationalisierung nachhaltiger KI-Lösungen. Sie lernen die Herausforderungen bei der Implementierung kennen, wie z. B. Probleme bei der KI-Operationalisierung und Hindernisse bei der Umsetzung von Erkenntnissen in umsetzbare Prognosen. Sie werden auch lernen, wie Sie die Schlüsselkomponenten der KI-Informationsarchitektur erkennen und welche Rolle sie für eine erfolgreiche und nachhaltige KI-Implementierung spielt. Und Sie werden verstehen, wie Sie KI effektiv einsetzen können, um die Nutzung von Kerninformationen in Master Data Management (MDM)-Lösungen zu verbessern.Was Sie lernen werdenVerstehen der wichtigsten KI-Konzepte, einschließlich maschinelles Lernen und Deep LearningBefolgen von Best Practices und Methoden zur erfolgreichen Bereitstellung und Operationalisierung von KI-LösungenErkennen der kritischen Komponenten der KI-Informationsarchitektur und der Bedeutung eines PlansIntegration von KI in bestehende Initiativen innerhalb einer OrganisationErkennen der aktuellen Grenzen von KI und wie sich dies auf Ihr Unternehmen auswirken könnteBewusstsein für wichtige und aktuelle KI-Forschung schaffenIhre Denkweise anpassen, um KI von einem ganzheitlichen Standpunkt aus zu betrachtenMachen Sie sich mit den Möglichkeiten von KI in verschiedenen Branchen vertraut.Für wen ist dieses Buch gedacht?IT-Profis, Datenwissenschaftler und Architekten, die sich mit den Herausforderungen bei der Implementierung und dem Betrieb von KI auseinandersetzen müssen und einen umfassenden Überblick darüber benötigen, wie sich KI auf andere geschäftskritische Bereiche auswirkt. Es ist keine Einführung, sondern richtet sich an Leser, die nach Beispielen für die Nutzung von Daten suchen, um daraus verwertbare Erkenntnisse und Vorhersagen abzuleiten, und die die aktuellen Risiken und Grenzen von KI verstehen und berücksichtigen müssen und wissen wollen, was dies in einem branchenrelevanten Kontext bedeutet.

This book introduces how to enhance the context capture ability of the model, improve the position information perception ability of the pretrained models, and identify and denoise the unlabeled entities. The Chinese medical named entity recognition is an important branch of the intelligent medicine, which is beneficial to mine the information hidden in medical texts and provide the medical entity information for clinical medical decision-making and medical classification. Researchers, engineers and post-graduate students in the fields of medicine management and software engineering.

This book presents recent developments in multivariate and robust statistical methods. Featuring contributions by leading experts in the field it covers various topics, including multivariate and high-dimensional methods, time series, graphical models, robust estimation, supervised learning and normal extremes. It will appeal to statistics and data science researchers, PhD students and practitioners who are interested in modern multivariate and robust statistics. The book is dedicated to David E. Tyler on the occasion of his pending retirement and also includes a review contribution on the popular Tyler¿s shape matrix.

This book discusses multi-agent technologies (MATs) and machine learning (ML). These tools can be integrated and applied in industry, commerce, energy, medicine, psychology, and other areas. This volume consists of six chapters in three sections that discuss the integration, applications, and advanced results of MATs and ML.