This book provides a survey of deep learning approaches to domain adaptation in computer vision. It gives the reader an overview of the state-of-the-art research in deep learning based domain adaptation. This book also discusses the various approaches to deep learning based domain adaptation in recent years. It outlines the importance of domain adaptation for the advancement of computer vision, consolidates the research in the area and provides the reader with promising directions for future research in domain adaptation. Divided into four parts, the first part of this book begins with an introduction to domain adaptation, which outlines the problem statement, the role of domain adaptation and the motivation for research in this area. It includes a chapter outlining pre-deep learning era domain adaptation techniques. The second part of this book highlights feature alignment based approaches to domain adaptation. The third part of this book outlines image alignment procedures for domain adaptation. The final section of this book presents novel directions for research in domain adaptation. This book targets researchers working in artificial intelligence, machine learning, deep learning and computer vision. Industry professionals and entrepreneurs seeking to adopt deep learning into their applications will also be interested in this book.

This book is written for software product teams that use AI to add intelligent models to their products or are planning to use it. As AI adoption grows, it is becoming important that all AI driven products can demonstrate they are not introducing any bias to the AI-based decisions they are making, as well as reducing any pre-existing bias or discrimination. The responsibility to ensure that the AI models are ethical and make responsible decisions does not lie with the data scientists alone. The product owners and the business analysts are as important in ensuring bias-free AI as the data scientists on the team. This book addresses the part that these roles play in building a fair, explainable and accountable model, along with ensuring model and data privacy. Each chapter covers the fundamentals for the topic and then goes deep into the subject matter - providing the details that enable the business analysts and the data scientists to implement these fundamentals. AI research is one of the most active and growing areas of computer science and statistics. This book includes an overview of the many techniques that draw from the research or are created by combining different research outputs. Some of the techniques from relevant and popular libraries are covered, but deliberately not drawn very heavily from as they are already well documented, and new research is likely to replace some of it.

This book gathers together much of the author's work - both old and new - to explore a number of the key increases in complexity seen in the natural world, seeking to explain each of them purely in terms of the features of fitness landscapes. In a very straightforward manner, the book introduces basic concepts to help readers follow the main ideas. By using variations of the NK model and including the concept of the Baldwin effect, the author presents new abstract models that are able to explain why sources of evolutionary innovation (genomes, symbiosis, sex, chromosomes, multicellularity) have been selected for and hence how complexity has increased over time in some lineages.

This book constitutes the refereed conference proceedings of the 19th International Conference on Web-Based Learning, ICWL 2020, and 5th International Symposium on Emerging Technologies for Education, SETE 2020, held in Ningbo, China in October 2020.Together for the ICWL 2020 Conference and SETE 2020 Symposium 39 full papers were accepted together with 31 short papers out of 233 submissions. The papers focus on the following subjects: Semantic Web for E-Learning, through Learning Analytics, Computer-Supported Collaborative Learning, Assessment, Pedagogical Issues, E-learning Platforms, and Tools, to Mobile Learning and much more.

This book constitutes the proceedings of the 11th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2020, as well as two challenges: M&Ms - The Multi-Centre, Multi-Vendor, Multi-Disease Segmentation Challenge, and EMIDEC - Automatic Evaluation of Myocardial Infarction from Delayed-Enhancement Cardiac MRI Challenge. The 43 full papers included in this volume were carefully reviewed and selected from 70 submissions. They deal with cardiac imaging and image processing, machine learning applied to cardiac imaging and image analysis, atlas construction, artificial intelligence, statistical modelling of cardiac function across different patient populations, cardiac computational physiology, model customization, atlas based functional analysis, ontological schemata for data and results, integrated functional and structural analyses, as well as the pre-clinical and clinical applicability of these methods.

This book emphasizes that learning efficiency of the learners can be increased by providing personalized course materials and guiding them to attune with suitable learning paths based on their characteristics such as learning style, knowledge level, emotion, motivation, self-efficacy and many more learning ability factors in e-learning system. Learning is a continuous process since human evolution. In fact, it is related to life and innovations. The basic objective of learning to grow, aspire and develop ease of life remains the same despite changes in the learning methodologies. Introduction of computers empowered us to attain new zenith in knowledge domain, developed pragmatic approach to solve life's problem and helped us to decipher different hidden patterns of data to get new ideas. Of late, computers are predominantly used in education. Its process has been changed from offline to online in view of enhancing the ease of learning. With the advent of information technology, e-learning has taken centre stage in educational domain. In e-learning context, developing adaptive e-learning system is buzzword among contemporary research scholars in the area of Educational Data Mining (EDM). Enabling personalized systems is meant for improvement in learning experience for learners as per their choices made or auto-detected needs. It helps in enhancing their performance in terms of knowledge, skills, aptitudes and preferences. It also enables speeding up the learning process qualitatively and quantitatively. These objectives are met only by the Personalized Adaptive E-learning Systems in this regard. Many noble frameworks were conceptualized, designed and developed to infer learning style preferences, and accordingly, learning materials were delivered adaptively to the learners. Designing frameworks help to measure learners' preferences minutely and provide adaptive learning materials to them in a way most appropriately.

This book addresses one of the most important unsolved problems in artificial intelligence: the task of learning, in an unsupervised manner, from massive quantities of spatiotemporal visual data that are available at low cost. The book covers important scientific discoveries and findings, with a focus on the latest advances in the field. Presenting a coherent structure, the book logically connects novel mathematical formulations and efficient computational solutions for a range of unsupervised learning tasks, including visual feature matching, learning and classification, object discovery, and semantic segmentation in video. The final part of the book proposes a general strategy for visual learning over several generations of student-teacher neural networks, along with a unique view on the future of unsupervised learning in real-world contexts. Offering a fresh approach to this difficult problem, several efficient, state-of-the-art unsupervised learning algorithms are reviewed in detail, complete with an analysis of their performance on various tasks, datasets, and experimental setups. By highlighting the interconnections between these methods, many seemingly diverse problems are elegantly brought together in a unified way. Serving as an invaluable guide to the computational tools and algorithms required to tackle the exciting challenges in the field, this book is a must-read for graduate students seeking a greater understanding of unsupervised learning, as well as researchers in computer vision, machine learning, robotics, and related disciplines.

The emerging biotechnologies have significantly advanced the study of biological mechanisms. However, biological data usually contain a great amount of missing information, e.g. missing features, missing labels or missing samples, which greatly limits the extensive usage of the data. In this book, we introduce different types of biological data missing scenarios and propose machine learning models to improve the data analysis, including deep recurrent neural network recovery for feature missings, robust information theoretic learning for label missings and structure-aware rebalancing for minor sample missings. Models in the book cover the fields of imbalance learning, deep learning, recurrent neural network and statistical inference, providing a wide range of references of the integration between artificial intelligence and biology. With simulated and biological datasets, we apply approaches to a variety of biological tasks, including single-cell characterization, genome-wide association studies, medical image segmentations, and quantify the performances in a number of successful metrics.The outline of this book is as follows. In Chapter 2, we introduce the statistical recovery of missing data features; in Chapter 3, we introduce the statistical recovery of missing labels; in Chapter 4, we introduce the statistical recovery of missing data sample information; finally, in Chapter 5, we summarize the full text and outlook future directions. This book can be used as references for researchers in computational biology, bioinformatics and biostatistics. Readers are expected to have basic knowledge of statistics and machine learning.

This two-volume set constitutes the refereed proceedings of the 16th International Conference on Collaborative Computing: Networking, Applications, and Worksharing, CollaborateCom 2020, held in Shanghai, China, in October 2020.The 61 full papers and 16 short papers presented were carefully reviewed and selected from 211 submissions. The papers reflect the conference sessions as follows: Collaborative Applications for Network and E-Commerce; Optimization for Collaborate System; Cloud and Edge Computing; Artificial Intelligence; AI Application and Optimization; Classification and Recommendation; Internet of Things; Collaborative Robotics and Autonomous Systems; Smart Transportation.

The two-volume set LNCS 12572 and 1273 constitutes the thoroughly refereed proceedings of the 27th International Conference on MultiMedia Modeling, MMM 2021, held in Prague, Czech Republic, in June2021. Of the 211 submitted regular papers, 40 papers were selected for oral presentation and 33 for poster presentation; 16 special session papers were accepted as well as 2 papers for a demo presentation and 17 papers for participation at the Video Browser Showdown 2021. The papers cover topics such as: multimedia indexing; multimedia mining; multimedia abstraction and summarization; multimedia annotation, tagging and recommendation; multimodal analysis for retrieval applications; semantic analysis of multimedia and contextual data; multimedia fusion methods; multimedia hyperlinking; media content browsing and retrieval tools; media representation and algorithms; audio, image, video processing, coding and compression; multimedia sensors and interaction modes; multimedia privacy, security and content protection; multimedia standards and related issues; advances in multimedia networking and streaming; multimedia databases, content delivery and transport; wireless and mobile multimedia networking; multi-camera and multi-view systems; augmented and virtual reality, virtual environments; real-time and interactive multimedia applications; mobile multimedia applications; multimedia web applications; multimedia authoring and personalization; interactive multimedia and interfaces; sensor networks; social and educational multimedia applications; and emerging trends.

This 8-volumes set constitutes the refereed of the 25th International Conference on Pattern Recognition Workshops, ICPR 2020, held virtually in Milan, Italy and rescheduled to January 10 - 11, 2021 due to Covid-19 pandemic. The 416 full papers presented in these 8 volumes were carefully reviewed and selected from about 700 submissions. The 46 workshops cover a wide range of areas including machine learning, pattern analysis, healthcare, human behavior, environment, surveillance, forensics and biometrics, robotics and egovision, cultural heritage and document analysis, retrieval, and women at ICPR2020.

This book reports on research and developments in human-technology interaction. A special emphasis is given to human-computer interaction, and its implementation for a wide range of purposes such as healthcare, manufacturing, transportation, and education, among others. The human aspects are analyzed in detail. Innovative studies related to human-centered design, wearable technologies, augmented, virtual and mixed reality simulation, as well as developments and applications of machine learning and AI for different purposes, represent the core of the book. Emerging issues in business, security, and infrastructure are also critically examined, thus offering a timely, scientifically-grounded, but also professionally-oriented snapshot of the current state of the field. The book is based on contributions presented at the 4th International Conference on Human Interaction and Emerging Technologies: Future Applications, IHIET-AI 2021, held on April 28-30, 2021, in Strasbourg, France. It offers a timely survey and a practice-oriented reference guide to researchers and professionals dealing with design and/or management of the new generation of service systems.

The 6-volume set, comprising the LNCS books 12535 until 12540, constitutes the refereed proceedings of 28 out of the 45 workshops held at the 16th European Conference on Computer Vision, ECCV 2020. The conference was planned to take place in Glasgow, UK, during August 23-28, 2020, but changed to a virtual format due to the COVID-19 pandemic. The 249 full papers, 18 short papers, and 21 further contributions included in the workshop proceedings were carefully reviewed and selected from a total of 467 submissions. The papers deal with diverse computer vision topics. Part I focusses on adversarial robustness in the real world; bioimage computation; egocentric perception, interaction and computing; eye gaze in VR, AR, and in the wild; TASK-CV workshop and VisDA challenge; and bodily expressed emotion understanding.

This book constitutes the First 3D Head and Neck Tumor Segmentation in PET/CT Challenge, HECKTOR 2020, which was held in conjunction with the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020, in Lima, Peru, in October 2020. The challenge took place virtually due to the COVID-19 pandemic.The 2 full and 8 short papers presented together with an overview paper in this volume were carefully reviewed and selected form numerous submissions. This challenge aims to evaluate and compare the current state-of-the-art methods for automatic head and neck tumor segmentation. In the context of this challenge, a dataset of 204 delineated PET/CT images was made available for training as well as 53 PET/CT images for testing. Various deep learning methods were developed by the participants with excellent results.

This book constitutes the refereed proceedings of the 16th China Conference on Machine Translation, CCMT 2020, held in Hohhot, China, in October 2020. The 13 papers presented in this volume were carefully reviewed and selected from 78 submissions and focus on all aspects of machine translation, including preprocessing, neural machine translation models, hybrid model, evaluation method, and post-editing.

This book covers the essential concepts and strategies within traditional and cutting-edge feature learning methods thru both theoretical analysis and case studies. Good features give good models and it is usually not classifiers but features that determine the effectiveness of a model. In this book, readers can find not only traditional feature learning methods, such as principal component analysis, linear discriminant analysis, and geometrical-structure-based methods, but also advanced feature learning methods, such as sparse learning, low-rank decomposition, tensor-based feature extraction, and deep-learning-based feature learning. Each feature learning method has its own dedicated chapter that explains how it is theoretically derived and shows how it is implemented for real-world applications. Detailed illustrated figures are included for better understanding. This book can be used by students, researchers, and engineers looking for a reference guide for popular methods of feature learning and machine intelligence.

At the dawn of the 4th Industrial Revolution, the field of Deep Learning (a sub-field of Artificial Intelligence and Machine Learning) is growing continuously and rapidly, developing both theoretically and towards applications in increasingly many and diverse other disciplines. The book at hand aims at exposing its reader to some of the most significant recent advances in deep learning-based technological applications and consists of an editorial note and an additional fifteen (15) chapters. All chapters in the book were invited from authors who work in the corresponding chapter theme and are recognized for their significant research contributions. In more detail, the chapters in the book are organized into six parts, namely (1) Deep Learning in Sensing, (2) Deep Learning in Social Media and IOT, (3) Deep Learning in the Medical Field, (4) Deep Learning in Systems Control, (5) Deep Learning in Feature Vector Processing, and (6) Evaluation of Algorithm Performance. This research book is directed towards professors, researchers, scientists, engineers and students in computer science-related disciplines. It is also directed towards readers who come from other disciplines and are interested in becoming versed in some of the most recent deep learning-based technological applications. An extensive list of bibliographic references at the end of each chapter guides the readers to probe deeper into their application areas of interest.

The fundamental algorithms in data mining and machine learning form the basis of data science, utilizing automated methods to analyze patterns and models for all kinds of data in applications ranging from scientific discovery to business analytics. This textbook for senior undergraduate and graduate courses provides a comprehensive, in-depth overview of data mining, machine learning and statistics, offering solid guidance for students, researchers, and practitioners. The book lays the foundations of data analysis, pattern mining, clustering, classification and regression, with a focus on the algorithms and the underlying algebraic, geometric, and probabilistic concepts. New to this second edition is an entire part devoted to regression methods, including neural networks and deep learning.

This book constitutes the proceedings of the 5th International Conference on Lean and Agile Software Development, LASD 2021, which was held online on January 23, 2021. The conference received a total of 32 submissions, of which 10 full and 2 short papers are included in this volume. In addition, one keynote paper is also included. To live the agile mindset, the LASD conference focuses on highly relevant research outcomes and fosters their way into practice. Topics discussed in this volume range from teams under COVID-19 through women in Agile, to product road-mapping and non-functional requirements.

This book sheds light on the challenges facing social media in combating malicious accounts, and aims to introduce current practices to address the challenges. It further provides an in-depth investigation regarding characteristics of "Pathogenic Social Media (PSM),"by focusing on how they differ from other social bots (e.g., trolls, sybils and cyborgs) and normal users as well as how PSMs communicate to achieve their malicious goals. This book leverages sophisticated data mining and machine learning techniques for early identification of PSMs, using the relevant information produced by these bad actors. It also presents proactive intelligence with a multidisciplinary approach that combines machine learning, data mining, causality analysis and social network analysis, providing defenders with the ability to detect these actors that are more likely to form malicious campaigns and spread harmful disinformation. Over the past years, social media has played a major role in massive dissemination of misinformation online. Political events and public opinion on the Web have been allegedly manipulated by several forms of accounts including "Pathogenic Social Media (PSM)" accounts (e.g., ISIS supporters and fake news writers). PSMs are key users in spreading misinformation on social media - in viral proportions. Early identification of PSMs is thus of utmost importance for social media authorities in an effort toward stopping their propaganda. The burden falls to automatic approaches that can identify these accounts shortly after they began their harmful activities. Researchers and advanced-level students studying and working in cybersecurity, data mining, machine learning, social network analysis and sociology will find this book useful. Practitioners of proactive cyber threat intelligence and social media authorities will also find this book interesting and insightful, as it presents an important and emerging type of threat intelligence facing social media and the general public.

The book discusses major technical advances and research findings in the field of machine intelligence in medical image analysis. It examines the latest technologies and that have been implemented in clinical practice, such as computational intelligence in computer-aided diagnosis, biological image analysis, and computer-aided surgery and therapy. This book provides insights into the basic science involved in processing, analysing, and utilising all aspects of advanced computational intelligence in medical decision-making based on medical imaging.

Dive into and apply practical machine learning and dataset categorization techniques while learning Tensorflow and deep learning. This book uses convolutional neural networks to do image recognition all in the familiar and easy to work with Swift language. It begins with a basic machine learning overview and then ramps up to neural networks and convolutions and how they work. Using Swift and Tensorflow, you'll perform data augmentation, build and train large networks, and build networks for mobile devices. You'll also cover cloud training and the network you build can categorize greyscale data, such as mnist, to large scale modern approaches that can categorize large datasets, such as imagenet. Convolutional Neural Networks with Swift for Tensorflow uses a simple approach that adds progressive layers of complexity until you have arrived at the current state of the art for this field. What You'll Learn Categorize and augment datasets Build and train large networks, including via cloud solutions Deploy complex systems to mobile devices Who This Book Is For Developers with Swift programming experience who would like to learn convolutional neural networks by example using Swift for Tensorflow as a starting point.

This book addresses the mapping of soil-landscape parameters in the geospatial domain. It begins by discussing the fundamental concepts, and then explains how machine learning and geomatics can be applied for more efficient mapping and to improve our understanding and management of 'soil'. The judicious utilization of a piece of land is one of the biggest and most important current challenges, especially in light of the rapid global urbanization, which requires continuous monitoring of resource consumption. The book provides a clear overview of how machine learning can be used to analyze remote sensing data to monitor the key parameters, below, at, and above the surface. It not only offers insights into the approaches, but also allows readers to learn about the challenges and issues associated with the digital mapping of these parameters and to gain a better understanding of the selection of data to represent soil-landscape relationships as well as the complex and interconnected links between soil-landscape parameters under a range of soil and climatic conditions. Lastly, the book sheds light on using the network of satellite-based Earth observations to provide solutions toward smart farming and smart land management.

This book constitutes the refereed proceedings of the 8th Language and Technology Conference: Challenges for Computer Science and Linguistics, LTC 2017, held in Poznan, Poland, in November 2017. The 26 revised papers presented in this volume were carefully reviewed and selected from 97 submissions. The papers selected to this volume belong to various fields of: Language Resources, Tools and Evaluation, Less-Resourced-Languages, Speech Processing, Morphology, Computational Semantics, Machine Translation, and Information Retrieval and Information Extraction.

This book constitutes the refereed proceedings of the Third International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2020, and the Second International Workshop on Radiogenomics in Neuro-oncology, RNO-AI 2020, held in conjunction with MICCAI 2020, in Lima, Peru, in October 2020.*For MLCN 2020, 18 papers out of 28 submissions were accepted for publication. The accepted papers present novel contributions in both developing new machine learning methods and applications of existing methods to solve challenging problems in clinical neuroimaging. For RNO-AI 2020, all 8 submissions were accepted for publication. They focus on addressing the problems of applying machine learning to large and multi-site clinical neuroimaging datasets. The workshop aimed to bring together experts in both machine learning and clinical neuroimaging to discuss and hopefully bridge the existing challenges of applied machine learning in clinical neuroscience. *The workshops were held virtually due to the COVID-19 pandemic.