Machine learning

Beg-Int user level

The thesis contains several pioneering results at the intersection of state-of-the-art materials characterization techniques and machine learning. The use of machine learning empowers the information extraction capability of neutron and photon spectroscopies. In particular, new knowledge and new physics insights to aid spectroscopic analysis may hold great promise for next-generation quantum technology. As a prominent example, the so-called proximity effect at topological material interfaces promises to enable spintronics without energy dissipation and quantum computing with fault tolerance, yet the characteristic spectral features to identify the proximity effect have long been elusive. The work presented within permits a fine resolution of its spectroscopic features and a determination of the proximity effect which could aid further experiments with improved interpretability. A few novel machine learning architectures are proposed in this thesis work which leverage the case when the data is scarce and utilize the internal symmetry of the system to improve the training quality. The work sheds light on future pathways to apply machine learning to augment experiments.

This book covers recent trends and applications of nonlinear dynamics in various branches of society, science, and engineering. The selected peer-reviewed contributions were presented at the International Conference on Nonlinear Dynamics and Applications (ICNDA 2022) at Sikkim Manipal Institute of Technology (SMIT) and cover a broad swath of topics ranging from chaos theory and fractals to quantum systems and the dynamics of the COVID-19 pandemic. Organized by the SMIT Department of Mathematics, this international conference offers an interdisciplinary stage for scientists, researchers, and inventors to present and discuss the latest innovations and trends in all possible areas of nonlinear dynamics.

Maschinelles Lernen (ML) ist zu einem alltäglichen Element in unserem Leben und zu einem Standardwerkzeug für viele Bereiche der Wissenschaft und Technik geworden. Um ML optimal nutzen zu können, ist es wichtig, die zugrunde liegenden Prinzipien zu verstehen. In diesem Buch wird ML als die rechnerische Umsetzung des wissenschaftlichen Prinzips betrachtet. Dieses Prinzip besteht darin, ein Modell eines gegebenen datenerzeugenden Phänomens kontinuierlich anzupassen, indem eine Form des Verlustes, der durch seine Vorhersagen entsteht, minimiert wird.Das Buch schult den Leser darin, verschiedene ML-Anwendungen und -Methoden in drei Komponenten (Daten, Modell und Verlust) aufzuschlüsseln, und hilft ihm so, aus dem riesigen Angebot an vorgefertigten ML-Methoden auszuwählen.Der Drei-Komponenten-Ansatz des Buches erlaubt eine einheitliche und transparente Darstellung verschiedener ML-Techniken. Wichtige Methoden zu Regularisierung, zum Schutz der Privatsphäre und zur Erklärbarkeit von ML-Methoden sind Spezialfälle dieses Drei-Komponenten-Ansatz.

This book first presents a tutorial on Federated Learning (FL) and its role in enabling Edge Intelligence over wireless edge networks. This provides readers with a concise introduction to the challenges and state-of-the-art approaches towards implementing FL over the wireless edge network. Then, in consideration of resource heterogeneity at the network edge, the authors provide multifaceted solutions at the intersection of network economics, game theory, and machine learning towards improving the efficiency of resource allocation for FL over the wireless edge networks. A clear understanding of such issues and the presented theoretical studies will serve to guide practitioners and researchers in implementing resource-efficient FL systems and solving the open issues in FL respectively.

A smart ecosystem is envisioned to exchange and analyze data across systems, enabling a flexible, faster, and reliable smart ecosystem for high-quality results at reduced costs and little human intervention. This book introduces many innovative approaches and provides solutions to various problems of smart ecosystems designed by employing various techniques/models based on AI, ML, Deep Learning, and the Internet of Things (IoT). The main focus is on intelligent multimedia processing and automated decision-making for various services, real-time data analysis, data security, cost-effective solutions for multimedia applications, smart information processing systems, and smart city planning to name a few. In addition, this book presents some key insights and future directions in the various areas of technology. Throughout the book, many state-of-the-art solutions concerning various applications are proposed to solve the issues and ensure the quality of services (QoS). The authors discuss the limitations of the current techniques used to design a smart ecosystem and highlight some prospective areas of research in the future. The book comprehensively discusses multimedia processing of various forms of data comprising text, images, and audio for the implementation of various solutions. The book is aimed to open many areas of research and thus would present a comprehensive reference for the design of smart ecosystems in various applications.

This book provides a collection of recent research works on learning from decentralized data, transferring information from one domain to another, and addressing theoretical issues on improving the privacy and incentive factors of federated learning as well as its connection with transfer learning and reinforcement learning. Over the last few years, the machine learning community has become fascinated by federated and transfer learning. Transfer and federated learning have achieved great success and popularity in many different fields of application. The intended audience of this book is students and academics aiming to apply federated and transfer learning to solve different kinds of real-world problems, as well as scientists, researchers, and practitioners in AI industries, autonomous vehicles, and cyber-physical systems who wish to pursue new scientific innovations and update their knowledge on federated and transfer learning and their applications.

This book provides a principled data-driven framework that progressively constructs, enriches, and applies taxonomies without leveraging massive human annotated data. Traditionally, people construct domain-specific taxonomies by extensive manual curations, which is time-consuming and costly. In today's information era, people are inundated with the vast amounts of text data. Despite their usefulness, people haven't yet exploited the full power of taxonomies due to the heavy curation needed for creating and maintaining them. To bridge this gap, the authors discuss automated taxonomy discovery and exploration, with an emphasis on label-efficient machine learning methods and their real-world usages. Taxonomy organizes entities and concepts in a hierarchy way. It is ubiquitous in our daily life, ranging from product taxonomies used by online retailers, topic taxonomies deployed by news outlets and social media, as well as scientific taxonomies deployed by digital libraries across various domains. When properly analyzed, these taxonomies can play a vital role for science, engineering, business intelligence, policy design, e-commerce, and more. Intuitive examples are used throughout enabling readers to grasp concepts more easily.

This book is designed to provide rich research hub for researchers, teachers, and students to ease research hassle/challenges. The book is rich and comprehensive enough to provide answers to frequently asked research questions because the content of the book touches several disciplines cutting across computing, engineering, medicine, education, and sciences in general. The rich multidisciplinary contents of the book promise to leave all users satisfied. The valuable features in the book include but not limited to: demonstration of mathematical expressions for implementation of machine learning models, integration of learning techniques, and projection of future AI and IoT technologies. These technologies will enable systems to be simulative, predictive, and self-operating smart systems. The primary audience of the book include but not limited to researchers, teachers, and postgraduate and undergraduate students in computing, engineering, medicine, education, and science fields.

This book offers insight into the current issues of the merger between reliability engineering and computational intelligence. The intense development of information technology allows for designing more complex systems as well as creating more detailed models of real-world systems which forces traditional reliability engineering approaches based on Boolean algebra, probability theory, and statistics to embrace the world of data science. The works deal with methodological developments as well as applications in the development of safe and reliable systems in various kinds of distribution networks, in the development of highly reliable healthcare systems, in finding weaknesses in systems with the human factor, or in reliability analysis of large information systems and other software solutions. In this book, experts from various fields of reliability engineering and computational intelligence present their view on the risks, the opportunities and the synergy between reliability engineering and computational intelligence that have been developed separately but in recent years have found a way to each other. The topics addressed include the latest advances in computing technology to improve the real lives of millions of people by increasing safety and reliability of various types of real-life systems by increasing the availability of software services, reducing the accident rate of means of transport, developing high reliable patient-specific health care, or generally, save cost and increase efficiency in the work and living environment. Though this book, the reader has access to professionals and researchers in the fields of reliability engineering and computational intelligence that share their experience in merging the two as well as an insight into the latest methods, concerns and application domains.

This book discusses the application of different machine learning techniques to the sub-concepts of smart cities such as smart energy, transportation, waste management, health, infrastructure, etc. The focus of this book is to come up with innovative solutions in the above-mentioned issues with the purpose of alleviating the pressing needs of human society. This book includes content with practical examples which are easy to understand for readers. It also covers a multi-disciplinary field and, consequently, it benefits a wide readership including academics, researchers, and practitioners.

This book analyses the implications of the technical, legal, ethical and privacy challenges as well as challenges for human rights and civil liberties regarding Artificial Intelligence (AI) and National Security. It also offers solutions that can be adopted to mitigate or eradicate these challenges wherever possible.As a general-purpose, dual-use technology, AI can be deployed for both good and evil. The use of AI is increasingly becoming of paramount importance to the government's mission to keep their nations safe. However, the design, development and use of AI for national security poses a wide range of legal, ethical, moral and privacy challenges. This book explores national security uses for Artificial Intelligence (AI) in Western Democracies and its malicious use. This book also investigates the legal, political, ethical, moral, privacy and human rights implications of the national security uses of AI in the aforementioned democracies. It illustrates how AI for national security purposes could threaten most individual fundamental rights, and how the use of AI in digital policing could undermine user human rights and privacy. In relation to its examination of the adversarial uses of AI, this book discusses how certain countries utilise AI to launch disinformation attacks by automating the creation of false or misleading information to subvert public discourse. With regards to the potential of AI for national security purposes, this book investigates how AI could be utilized in content moderation to counter violent extremism on social media platforms. It also discusses the current practices in using AI in managing Big Data Analytics demands. This book provides a reference point for researchers and advanced-level students studying or working in the fields of Cyber Security, Artificial Intelligence, Social Sciences, Network Security as well as Law and Criminology. Professionals working within these related fields and law enforcement employees will also find this book valuable as a reference.

Artificial Intelligence has revolutionised areas of medicine. This book focuses on the integral role of AI in radiology, shedding light on how this technology can enhance patient care and streamline professional workflows.

The book presents high quality research papers presented at International Conference on Computational Intelligence (ICCI 2021) held online during 27-28 December, 2021. The topics covered are artificial intelligence, neural network, deep learning techniques, fuzzy theory and systems, rough sets, self-organizing maps, machine learning, chaotic systems, multi-agent systems, computational optimization ensemble classifiers, reinforcement learning, decision trees, support vector machines, hybrid learning, statistical learning. metaheuristics algorithms: evolutionary and swarm-based algorithms like genetic algorithms, genetic programming, differential evolution, particle swarm optimization, whale optimization, spider monkey optimization, firefly algorithm, memetic algorithms. And also machine vision, Internet of Things, image processing, image segmentation, data clustering, sentiment analysis, big data, computer networks, signal processing, supply chain management, web and text mining, distributed systems, bioinformatics, embedded systems, expert system, forecasting, pattern recognition, planning and scheduling, time series analysis, human-computer interaction, web mining, natural language processing, multimedia systems, and quantum computing.

How do you teach computers to learn from data?This hands-on introduction teaches the basics of machine learning with R, H2O and Keras using numerous examples. You will be able to select the appropriate approach and apply it to your own questions such as image classification or predictions.Since erroneous data can jeopardize learning success, special attention is paid to data preparation and analysis. For this purpose, R provides highly developed and scientifically sound analysis libraries, the functionality and application of which are shown.You will learn for which applications statistical methods such as regression, classification, factor, cluster and time series analysis are sufficient and when it is better to use neural networks such as e.g. B. CNNs or RNNs should work. The H20 framework and Keras are used here.Examples show how you can analyze stumbling blocks in the learning process or how to avoid them from the outset. You will also learn under what circumstances you can reuse the results of machine learning and how to do this.This book is a translation of "Maschinelles Lernen mit R", Carl Hanser Verlag, ISBN 978-3446471658

Learn and implement responsible AI models using Python. This book will teach you how to balance ethical challenges with opportunities in artificial intelligence.The book starts with an introduction to the fundamentals of AI, with special emphasis given to the key principles of responsible AI. The authors then walk you through the critical issues of detecting and mitigating bias, making AI decisions understandable, preserving privacy, ensuring security, and designing robust models. Along the way, yoüll gain an overview of tools, techniques, and code examples to implement the key principles you learn in real-world scenarios.The book concludes with a chapter devoted to fostering a deeper understanding of responsible AI¿s profound implications for the future. Each chapter offers a hands-on approach, enriched with practical insights and code snippets, enabling you to translate ethical considerations into actionable solutions. What You Will LearnUnderstand the principles of responsible AI and their importance in today's digital worldMaster techniques to detect and mitigate bias in AIExplore methods and tools for achieving transparency and explainabilityDiscover best practices for privacy preservation and security in AIGain insights into designing robust and reliable AI modelsWho This Book Is ForAI practitioners, data scientists, machine learning engineers, researchers, policymakers, and students interested in the ethical aspects of AI

Maschinelles Lernen und künstliche Intelligenz sind omnipräsente Begriffe zur Verbesserung von technischen Prozessen. Die praktische Umsetzung an realen Problemen gestaltet sich aber oft schwierig und komplex. Dieses Lehrbuch erklärt Lernverfahren anhand von analytischen Konzepten im Zusammenspiel mit vollständigen Programmierbeispielen in Python und bezieht sich auf dabei stets auf reale technische Anwendungsszenarien. Es zeigt den Einsatz physikalisch-informierter Lernstrategien, die Einbeziehung von Unsicherheit in die Modellierung und den Aufbau von erklärbarer, vertrauenswürdiger künstlicher Intelligenz mit Hilfe spezialisierter Datenbanken.Dieses Lehrbuch richtet sich somit sowohl an Studierende der Ingenieurswissenschaften, Naturwissenschaft, Medizin und Betriebswirtschaft als auch an Anwender aus der Industrie (vor allem Data Scientists), Entwickler*innen von Expertendatenbanken und Softwareentwickler*innen.

Synthetic Symmetry: A New Approach to Lie Theory" takes readers on an intellectual journey into the fascinating world of abstract algebra and its applications in modern mathematics and science. This groundbreaking book introduces a fresh perspective on Lie theory, a field renowned for its profound insights into symmetries, transformations, and the fundamental structure of mathematical objects.With clarity and precision, this book presents the innovative concept of "synthetic symmetry," offering a unique framework for understanding and exploring the intricate symmetries that permeate the mathematical universe. It reimagines traditional Lie theory, providing a more intuitive and accessible approach that appeals to both seasoned mathematicians and those new to the field.Through compelling explanations, insightful examples, and practical applications, "Synthetic Symmetry" demonstrates how this novel perspective can shed new light on a wide range of mathematical problems and scientific phenomena. Whether you are a mathematics enthusiast, a student, or a professional mathematician, this book will expand your understanding of symmetries and their role in shaping the mathematical and physical world.This book is an indispensable resource for anyone seeking a deeper appreciation of symmetry and its significance in mathematics, physics, and beyond. It challenges conventional thinking and invites readers to explore the beauty and elegance of synthetic symmetry, making it an essential addition to the library of anyone passionate about the mathematical sciences.

This book constitutes the proceedings of the 16th International Conference on Social, Cultural, and Behavioral Modeling, SBP-BRiMS 2023, which was held in Pittsburgh, PA, USA in September 2023.The 31 full papers presented in this volume were carefully reviewed and selected from 73 submissions. The papers were organized in topical sections as follows: Detecting malign influence; human behavior modeling; and social-cyber behavior modeling.

The surge in renewable and distributed energy sources has posed significant challenges for smart power distribution network (SPDN). These challenges fall into two main categories: the unpredictability of renewable energy sources and the complexities introduced by numerous electrical devices and their interdependencies, affecting forecasting and operational performance. As the emphasis on SPDN's economic and environmental aspects grows, this book focuses on the vital themes of sustainability and cost-efficiency in SPDN forecasting, planning, and operation. It is structured into three key parts:1. SPDN Situation Awareness: This section assesses prior research methods, analyzes their shortcomings while dissecting SPDN's unique situation awareness characteristics. Then, some forecast and virtual collection methods are presented. 2. Boosting SPDN Planning: Addressing optimal planning challenges in SPDN, this part introduces advanced modelling and algorithm solvingtechniques, tailored to mitigate SPDN's inherent uncertainty.3. Enhancing SPDN Operation: Considering a variety of equipment types and controllable loads, this section explores strategies to boost SPDN operational performance. It covers control methodologies for electric vehicles, flexible loads, energy storage, and related equipments, etc.Tailored for university researchers, engineers, and graduate students in electrical engineering and computer science, this book is a valuable resource for comprehending SPDN's situation awareness, planning, and operation intricacies in the context of sustainability and economic efficiency.

This volume contains select papers presented during the 4th  National Conference on Multidisciplinary Analysis and Optimization. It discusses new developments at the core of optimization methods and their application in multiple applications. The papers showcase fundamental problems and applications which include domains such as aerospace, automotive and industrial sectors. The variety of topics and diversity of insights presented in the general field of optimization and its use in design for different applications will be of interest to researchers in academia or industry.

This 3rd edition tackles the basic principle of deep learning as well as the application of combination of wavelet theory with deep learning to pattern recognition. Five new chapters related to the combination of wavelet theory and deep learning are added with many novel research results.The useful reference text will benefit academics, researchers, computer scientists, electronic engineers and graduate students in the field of pattern recognition, image analysis, machine learning and electrical and electronic engineering.

This book helps and promotes the use of machine learning tools and techniques in econometrics and explains how machine learning can enhance and expand the econometrics toolbox in theory and in practice. Throughout the volume, the authors raise and answer six questions: 1) What are the similarities between existing econometric and machine learning techniques? 2) To what extent can machine learning techniques assist econometric investigation? Specifically, how robust or stable is the prediction from machine learning algorithms given the ever-changing nature of human behavior? 3) Can machine learning techniques assist in testing statistical hypotheses and identifying causal relationships in 'big data? 4) How can existing econometric techniques be extended by incorporating machine learning concepts? 5) How can new econometric tools and approaches be elaborated on based on machine learning techniques? 6) Is it possible to develop machine learning techniques further and make them even more readily applicable in econometrics?As the data structures in economic and financial data become more complex and models become more sophisticated, the book takes a multidisciplinary approach in developing both disciplines of machine learning and econometrics in conjunction, rather than in isolation. This volume is a must-read for scholars, researchers, students, policy-makers, and practitioners, who are using econometrics in theory or in practice. 

This book highlights recent advances in smart cities technologies, with a focus on new technologies such as biometrics, blockchains, data encryption, data mining, machine learning, deep learning, cloud security, and mobile security.  During the past five years, digital cities have been emerging as a technology reality that will come to dominate the usual life of people, in either developed or developing countries. Particularly, with big data issues from smart cities, privacy and security have been a widely concerned matter due to its relevance and sensitivity extensively present in cybersecurity, healthcare, medical service, e-commercial, e-governance, mobile banking, e-finance, digital twins, and so on. These new topics rises up with the era of smart cities and mostly associate with public sectors, which are vital to the modern life of people. This volume summarizes the recent advances in addressing the challenges on big data privacy and security in smart cities and points out the future research direction around this new challenging topic.

This book gathers selected papers presented at International Conference on Machine Learning, Advances in Computing, Renewable Energy and Communication (MARC 2021), held in Krishna Engineering College, Ghaziabad, India, during 10 - 11 December, 2021. This book discusses key concepts, challenges and potential solutions in connection with established and emerging topics in advanced computing, renewable energy and network communications.

This volume LNCS 14127 constitutes the refereed proceedings of the 5th International Workshop, EXTRAAMAS 2023, held in London, UK, in May 2023. The 15 full papers presented together with 1 short paper were carefully reviewed and selected from 26 submissions. The workshop focuses on Explainable Agents and multi-agent systems; Explainable Machine Learning; and Cross-domain applied XAI.