Many approaches have sprouted from artificial intelligence (AI) and produced major breakthroughs in the computer science and engineering industries. Deep learning is a method that is transforming the world of data and analytics. Optimization of this new approach is still unclear, however, and there's a need for research on the various applications and techniques of deep learning in the field of computing. Deep Learning Techniques and Optimization Strategies in Big Data Analytics is a collection of innovative research on the methods and applications of deep learning strategies in the fields of computer science and information systems. While highlighting topics including data integration, computational modeling, and scheduling systems, this book is ideally designed for engineers, IT specialists, data analysts, data scientists, engineers, researchers, academicians, and students seeking current research on deep learning methods and its application in the digital industry.

Reinforcement learning (RL) is one of the foundational pillars of artificial intelligence and machine learning. An important consideration in any optimization or control problem is the notion of risk, but its incorporation into RL has been a fairly recent development. This monograph surveys research on risk-sensitive RL that uses policy gradient search. The authors survey some of the recent work in this area specifically where policy gradient search is the solution approach. In the first risk-sensitive RL setting, they cover popular risk measures based on variance, conditional value at-risk and chance constraints, and present a template for policy gradient-based risk-sensitive RL algorithms using a Lagrangian formulation. For the setting where risk is incorporated directly into the objective function, they consider an exponential utility formulation, cumulative prospect theory, and coherent risk measures. Written for novices and experts alike the authors have made the text completely self-contained but also organized in a manner that allows expert readers to skip background chapters. This is a complete guide for students and researchers working on this aspect of machine learning.

Machine Learning for Subsurface Characterization develops and applies neural networks, random forests, deep learning, unsupervised learning, Bayesian frameworks, and clustering methods for subsurface characterization. Machine learning (ML) focusses on developing computational methods/algorithms that learn to recognize patterns and quantify functional relationships by processing large data sets, also referred to as the "big data." Deep learning (DL) is a subset of machine learning that processes "big data" to construct numerous layers of abstraction to accomplish the learning task. DL methods do not require the manual step of extracting/engineering features; however, it requires us to provide large amounts of data along with high-performance computing to obtain reliable results in a timely manner. This reference helps the engineers, geophysicists, and geoscientists get familiar with data science and analytics terminology relevant to subsurface characterization and demonstrates the use of data-driven methods for outlier detection, geomechanical/electromagnetic characterization, image analysis, fluid saturation estimation, and pore-scale characterization in the subsurface.

Advances in Domain Adaptation Theory gives current, state-of-the-art results on transfer learning, with a particular focus placed on domain adaptation from a theoretical point-of-view. The book begins with a brief overview of the most popular concepts used to provide generalization guarantees, including sections on Vapnik-Chervonenkis (VC), Rademacher, PAC-Bayesian, Robustness and Stability based bounds. In addition, the book explains domain adaptation problem and describes the four major families of theoretical results that exist in the literature, including the Divergence based bounds. Next, PAC-Bayesian bounds are discussed, including the original PAC-Bayesian bounds for domain adaptation and their updated version. Additional sections present generalization guarantees based on the robustness and stability properties of the learning algorithm.

Brain-machine interfacing or brain-computer interfacing (BMI/BCI) is an emerging and challenging technology used in engineering and neuroscience. The ultimate goal is to provide a pathway from the brain to the external world via mapping, assisting, augmenting or repairing human cognitive or sensory-motor functions. In this book an international panel of experts introduce signal processing and machine learning techniques for BMI/BCI and outline their practical and future applications in neuroscience, medicine, and rehabilitation, with a focus on EEG-based BMI/BCI methods and technologies. Topics covered include discriminative learning of connectivity pattern of EEG; feature extraction from EEG recordings; EEG signal processing; transfer learning algorithms in BCI; convolutional neural networks for event-related potential detection; spatial filtering techniques for improving individual template-based SSVEP detection; feature extraction and classification algorithms for image RSVP based BCI; decoding music perception and imagination using deep learning techniques; neurofeedback games using EEG-based Brain-Computer Interface Technology; affective computing system and more.

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

Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques: A MATLAB Based Approach presents how machine learning and biomedical signal processing methods can be used in biomedical signal analysis. Different machine learning applications in biomedical signal analysis, including those for electrocardiogram, electroencephalogram and electromyogram are described in a practical and comprehensive way, helping readers with limited knowledge. Sections cover biomedical signals and machine learning techniques, biomedical signals, such as electroencephalogram (EEG), electromyogram (EMG) and electrocardiogram (ECG), different signal-processing techniques, signal de-noising, feature extraction and dimension reduction techniques, such as PCA, ICA, KPCA, MSPCA, entropy measures, and other statistical measures, and more. This book is a valuable source for bioinformaticians, medical doctors and other members of the biomedical field who need a cogent resource on the most recent and promising machine learning techniques for biomedical signals analysis.

Source Separation and Machine Learning presents the fundamentals in adaptive learning algorithms for Blind Source Separation (BSS) and emphasizes the importance of machine learning perspectives. It illustrates how BSS problems are tackled through adaptive learning algorithms and model-based approaches using the latest information on mixture signals to build a BSS model that is seen as a statistical model for a whole system. Looking at different models, including independent component analysis (ICA), nonnegative matrix factorization (NMF), nonnegative tensor factorization (NTF), and deep neural network (DNN), the book addresses how they have evolved to deal with multichannel and single-channel source separation.

Based on current literature and cutting-edge advances in the machine learning field, there are four algorithms whose usage in new application domains must be explored: neural networks, rule induction algorithms, tree-based algorithms, and density-based algorithms. A number of machine learning related algorithms have been derived from these four algorithms. Consequently, they represent excellent underlying methods for extracting hidden knowledge from unstructured data, as essential data mining tasks. Implementation of Machine Learning Algorithms Using Control-Flow and Dataflow Paradigms presents widely used data-mining algorithms and explains their advantages and disadvantages, their mathematical treatment, applications, energy efficient implementations, and more. It presents research of energy efficient accelerators for machine learning algorithms. Covering topics such as control-flow implementation, approximate computing, and decision tree algorithms, this book is an essential resource for computer scientists, engineers, students and educators of higher education, researchers, and academicians.

Artificial intelligence has been utilized in a diverse range of industries as more people and businesses discover its many uses and applications. A current field of study that requires more attention, as there is much opportunity for improvement, is the use of artificial intelligence within literary works and social media analysis. Artificial Intelligence Applications in Literary Works and Social Media presents contemporary developments in the adoption of artificial intelligence in textual analysis of literary works and social media and introduces current approaches, techniques, and practices in data science that are implemented to scrap and analyze text data. This book initiates a new multidisciplinary field that is the combination of artificial intelligence, data science, social science, literature, and social media study. Covering key topics such as opinion mining, sentiment analysis, and machine learning, this reference work is ideal for computer scientists, industry professionals, researchers, scholars, practitioners, academicians, instructors, and students.

Machine Learning is evolving computation and its application like never before. It is now widely recognized that machine learning is playing a similar role as electricity played in modernizing the world. From simple high school science projects to large-scale radio astronomy, machine learning has revolutionized it all. However, a few of the applications stand out as transforming the world and opening up a new era. The book intends to showcase applications of machine learning that are leading us to the next generation of computing and living standards. The book portrays the application of machine learning to cutting-edge technologies that are playing a prominent role in improving the quality of life and the progress of civilization. The focus of the book is not just machine learning, but its application to specific domains that are resulting in substantial progress of civilization. It is ideal for scientists and researchers, academic and corporate libraries, students, lecturers and teachers, and practitioners and professionals.

Evolution of Knowledge Science: Myth to Medicine: Intelligent Internet-Based Humanist Machines explains how to design and build the next generation of intelligent machines that solve social and environmental problems in a systematic, coherent, and optimal fashion. The book brings together principles from computer and communication sciences, electrical engineering, mathematics, physics, social sciences, and more to describe computer systems that deal with knowledge, its representation, and how to deal with knowledge centric objects. Readers will learn new tools and techniques to measure, enhance, and optimize artificial intelligence strategies for efficiently searching through vast knowledge bases, as well as how to ensure the security of information in open, easily accessible, and fast digital networks. Author Syed Ahamed joins the basic concepts from various disciplines to describe a robust and coherent knowledge sciences discipline that provides readers with tools, units, and measures to evaluate the flow of knowledge during course work or their research. He offers a unique academic and industrial perspective of the concurrent dynamic changes in computer and communication industries based upon his research. The author has experience both in industry and in teaching graduate level telecommunications and network architecture courses, particularly those dealing with applications of networks in education.

This book constitutes the refereed post-conference proceedings of the Fourth IFIP TC 12 International Conference on Computational Intelligence in Data Science, ICCIDS 2021, held in Chennai, India, in March 2021. The 20 revised full papers presented were carefully reviewed and selected from 75 submissions. The papers cover topics such as computational intelligence for text analysis; computational intelligence for image and video analysis; blockchain and data science.

This book offers an introduction into quantum machine learning research, covering approaches that range from "near-term" to fault-tolerant quantum machine learning algorithms, and from theoretical to practical techniques that help us understand how quantum computers can learn from data. Among the topics discussed are parameterized quantum circuits, hybrid optimization, data encoding, quantum feature maps and kernel methods, quantum learning theory, as well as quantum neural networks. The book aims at an audience of computer scientists and physicists at the graduate level onwards. The second edition extends the material beyond supervised learning and puts a special focus on the developments in near-term quantum machine learning seen over the past few years.

Phishing is one of the most widely-perpetrated forms of cyber attack, used to gather sensitive information such as credit card numbers, bank account numbers, and user logins and passwords, as well as other information entered via a web site. The authors of A Machine-Learning Approach to Phishing Detetion and Defense have conducted research to demonstrate how a machine learning algorithm can be used as an effective and efficient tool in detecting phishing websites and designating them as information security threats. This methodology can prove useful to a wide variety of businesses and organizations who are seeking solutions to this long-standing threat. A Machine-Learning Approach to Phishing Detetion and Defense also provides information security researchers with a starting point for leveraging the machine algorithm approach as a solution to other information security threats.

This book encompasses a systematic exploration of Cybersecurity Data Science (CSDS) as an emerging profession, focusing on current versus idealized practice. This book also analyzes challenges facing the emerging CSDS profession, diagnoses key gaps, and prescribes treatments to facilitate advancement. Grounded in the management of information systems (MIS) discipline, insights derive from literature analysis and interviews with 50 global CSDS practitioners. CSDS as a diagnostic process grounded in the scientific method is emphasized throughout Cybersecurity Data Science (CSDS) is a rapidly evolving discipline which applies data science methods to cybersecurity challenges. CSDS reflects the rising interest in applying data-focused statistical, analytical, and machine learning-driven methods to address growing security gaps. This book offers a systematic assessment of the developing domain. Advocacy is provided to strengthen professional rigor and best practices in the emerging CSDS profession. This book will be of interest to a range of professionals associated with cybersecurity and data science, spanning practitioner, commercial, public sector, and academic domains. Best practices framed will be of interest to CSDS practitioners, security professionals, risk management stewards, and institutional stakeholders. Organizational and industry perspectives will be of interest to cybersecurity analysts, managers, planners, strategists, and regulators. Research professionals and academics are presented with a systematic analysis of the CSDS field, including an overview of the state of the art, a structured evaluation of key challenges, recommended best practices, and an extensive bibliography.

This book uses machine-learning to identify the causes of conflict from among the top predictors of conflict. This methodology elevates some complex causal pathways that cause civil conflict over others, thus teasing out the complex interrelationships between the most important variables that cause civil conflict. Success in this realm will lead to scientific theories of conflict that will be useful in preventing and ending civil conflict. After setting out a current review of the literature and a case for using machine learning to analyze and predict civil conflict, the authors lay out the data set, important variables, and investigative strategy of their methodology. The authors then investigate institutional causes, economic causes, and sociological causes for civil conflict, and how that feeds into their model. The methodology provides an identifiable pathway for specifying causal models. This book will be of interest to scholars in the areas of economics, political science, sociology, and artificial intelligence who want to learn more about leveraging machine learning technologies to solve problems and who are invested in preventing civil conflict.

This book provides a snapshot of the state of current research at the interface between machine learning and healthcare with special emphasis on machine learning projects that are (or are close to) achieving improvement in patient outcomes. The book provides overviews on a range of technologies including detecting artefactual events in vital signs monitoring data; patient physiological monitoring; tracking infectious disease; predicting antibiotic resistance from genomic data; and managing chronic disease. With contributions from an international panel of leading researchers, this book will find a place on the bookshelves of academic and industrial researchers and advanced students working in healthcare technologies, biomedical engineering, and machine learning.