This book presents fundamental topics and algorithms that form the core of machine learning (ML) research, as well as emerging paradigms in intelligent system design. The multidisciplinary nature of machine learning makes it a very fascinating and popular area for research. The book is aiming at students, practitioners and researchers and captures the diversity and richness of the field of machine learning and intelligent systems. Several chapters are devoted to computational learning models such as granular computing, rough sets and fuzzy sets An account of applications of well-known learning methods in biometrics, computational stylistics, multi-agent systems, spam classification including an extremely well-written survey on Bayesian networks shed light on the strengths and weaknesses of the methods. Practical studies yielding insight into challenging problems such as learning from incomplete and imbalanced data, pattern recognition of stochastic episodic events and on-line mining of non-stationary data streams are a key part of this book.

This book presents recent machine learning paradigms and advances in learning analytics, an emerging research discipline concerned with the collection, advanced processing, and extraction of useful information from both educators’ and learners’ data with the goal of improving education and learning systems. In this context, internationally respected researchers present various aspects of learning analytics and selected application areas, including: • Using learning analytics to measure student engagement, to quantify the learning experience and to facilitate self-regulation; • Using learning analytics to predict student performance; • Using learning analytics to create learning materials and educational courses; and • Using learning analytics as a tool to support learners and educators in synchronous and asynchronous eLearning. The book offers a valuable asset for professors, researchers, scientists, engineers and students of all disciplines. Extensive bibliographies at the end of each chapter guide readers to probe further into their application areas of interest.

EMERGING COMPUTING PARADIGMS A holistic overview of major new computing paradigms of the 21st Century In Emerging Computing Paradigms: Principles, Advances and Applications, international scholars offer a compendium of essential knowledge on new promising computing paradigms. The book examines the characteristics and features of emerging computing technologies and provides insight into recent technological developments and their potential real-world applications that promise to shape the future. This book is a useful resource for all those who wish to quickly grasp new concepts of, and insights on, emerging computer paradigms and pursue further research or innovate new novel applications harnessing these concepts. Key Features Presents a comprehensive coverage of new technologies that have the potential to shape the future of our world—quantum computing, computational intelligence, advanced wireless networks and blockchain technology Revisits mainstream ideas now being widely adopted, such as cloud computing, the Internet of Things (IoT) and cybersecurity Offers recommendations and practical insights to assist the readers in the application of these technologies Aimed at IT professionals, educators, researchers, and students, Emerging Computing Paradigms: Principles, Advances and Applications is a comprehensive resource to get ahead of the curve in examining and exploiting emerging new concepts and technologies. Business executives will also find the book valuable and gain an advantage over competitors in harnessing the concepts examined therein.

Introduces machine learning and its algorithmic paradigms, explaining the principles behind automated learning approaches and the considerations underlying their usage.

This book constitutes the refereed proceedings of the First International Conference on Advanced Machine Learning Technologies and Applications, AMLTA 2012, held in Cairo, Egypt, in December 2012. The 58 full papers presented were carefully reviewed and selected from 99 intial submissions. The papers are organized in topical sections on rough sets and applications, machine learning in pattern recognition and image processing, machine learning in multimedia computing, bioinformatics and cheminformatics, data classification and clustering, cloud computing and recommender systems.

Learning is a key issue in the analysis and design of all kinds of intelligent systems. In recent time many new paradigms of automated (machine) learning have been proposed in the literature. Soft computing, that has proved to be an effective and efficient tool in so many areas of science and technology, seems to offer new qualities in the realm of machine learning too. The purpose of this volume is to present some new learning paradigms that have been triggered, or at least strongly influenced by soft computing tools and techniques, mainly related to neural networks, fuzzy logic, rough sets, and evolutionary computations.

This interdisciplinary book explores the intersection of literature, education, gender equality, and the digital revolution. We welcome original research, critical essays, and theoretical discussions that delve into the evolving dynamics shaping these areas.

Lifelong Machine Learning, Second Edition is an introduction to an advanced machine learning paradigm that continuously learns by accumulating past knowledge that it then uses in future learning and problem solving. In contrast, the current dominant machine learning paradigm learns in isolation: given a training dataset, it runs a machine learning algorithm on the dataset to produce a model that is then used in its intended application. It makes no attempt to retain the learned knowledge and use it in subsequent learning. Unlike this isolated system, humans learn effectively with only a few examples precisely because our learning is very knowledge-driven: the knowledge learned in the past helps us learn new things with little data or effort. Lifelong learning aims to emulate this capability, because without it, an AI system cannot be considered truly intelligent. Research in lifelong learning has developed significantly in the relatively short time since the first edition of this book was published. The purpose of this second edition is to expand the definition of lifelong learning, update the content of several chapters, and add a new chapter about continual learning in deep neural networks—which has been actively researched over the past two or three years. A few chapters have also been reorganized to make each of them more coherent for the reader. Moreover, the authors want to propose a unified framework for the research area. Currently, there are several research topics in machine learning that are closely related to lifelong learning—most notably, multi-task learning, transfer learning, and meta-learning—because they also employ the idea of knowledge sharing and transfer. This book brings all these topics under one roof and discusses their similarities and differences. Its goal is to introduce this emerging machine learning paradigm and present a comprehensive survey and review of the important research results and latest ideas in the area. This book is thus suitable for students, researchers, and practitioners who are interested in machine learning, data mining, natural language processing, or pattern recognition. Lecturers can readily use the book for courses in any of these related fields.

Multidisciplinary approach in research is very much in vogue these days to address the problems of the society. It involves drawing appropriately from multiple disciplines to explore problems outside the normal boundaries and reach out to solutions addressed through different perspectives. Modern research looks through more multidisciplinary approaches and has dominance of problem solving and project oriented applied research. Multidisciplinary approaches while aiming at achieving a common goal attempts to develop answers to complex questions, which a single discipline is unable to handle. The growing research canon is to apply knowledge of various disciplines for the solution. Since current problems are of complex nature, there is a need to have knowledge of all the aspects such as economic, social, political and psychological. Multi-disciplinary approaches call for collaboration between two or more disciplines on a research project, while each discipline maintaining its assumptions, values, and methods. In other words, each discipline maintains its autonomy while collaborating. Today multidisciplinary approach is considered as the driver of innovation and research to solve real world problems. The book aims to address the current issues and problems and draw the solutions with the help of multidisciplinary approaches. Key Features · Highlights the aspects of experiential marketing in higher education institutions, social and emotional learning for children, customer relationship and purchase intention of customers on digital platform, theoretical contribution and evaluation of HRA, Normative susceptibility towards counterfeit branded products, workplace spirituality in enhancing employee well-being and artworks revolved around the religious deities and kings. · Describes innovative solutions towards excess runoff, continuous monitoring of train parameters, recovering the infected individuals and reduction of their number, compete for achieving the growth and respectable market share, security and privacy issues with the Smart Contract and improve the security of the blockchain technology. · Throws light on the techniques and their applications for Emperor Penguin Optimizer as a new power allocation approach, Latent finger-marks, QCA technology, better retrieval of invisible texts. · Focuses on gold has a strong hedge, economic impact of Mughals on Assamese society, Indian exports for improving productivity, loan repayment behaviours of the borrowers, positive attitude towards Swayam Courses. Academicians, researchers, practitioners, and students would be benefitted by reading this book.

Artificial Intelligence (AI) is widely known as a knowledge field that aims to make computers, robots, or products that mimic the way humans think. In the current scientific community, AI is an intensively studied area composed of multiple branches. Historically, machine learning and optimization are two of the most studied fronts thanks to the development of novel and challenging research topics such as transfer optimization, swarm robotics, and drift detection and adaptation to evolving conditions in real-time. This book collects radically new theoretical insights, reporting recent developments and evincing innovative applications regarding AI methods in all fields of knowledge. It also presents works focused on new paradigms and novel branches of AI science.