Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This 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 metalearning--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.

Machine learning. --- lifelong machine learning --- lifelong learning --- continuous learning --- continual learning --- meta-learning --- never-ending learning --- multi-task learning --- transfer learning --- Learning, Machine --- Artificial intelligence --- Machine theory --- Machine learning

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Deep learning has been revolutionizing many fields in computer vision, and facial informatics is one of the major fields. Novel approaches and performance breakthroughs are often reported on existing benchmarks. As the performances on existing benchmarks are close to saturation, larger and more challenging databases are being made and considered as new benchmarks, further pushing the advancement of the technologies. Considering face recognition, for example, the VGG-Face2 and Dual-Agent GAN report nearly perfect and better-than-human performances on the IARPA Janus Benchmark A (IJB-A) benchmark. More challenging benchmarks, e.g., the IARPA Janus Benchmark A (IJB-C), QMUL-SurvFace and MegaFace, are accepted as new standards for evaluating the performance of a new approach. Such an evolution is also seen in other branches of face informatics. In this Special Issue, we have selected the papers that report the latest progresses made in the following topics: 1. Face liveness detection 2. Emotion classification 3. Facial age estimation 4. Facial landmark detection We are hoping that this Special Issue will be beneficial to all fields of facial informatics.

History of engineering & technology --- deep learning --- RGB --- depth --- facial landmarking --- merging networks --- 3D geometry data --- 2D attribute maps --- fused CNN feature --- coarse-to-fine --- convolutional neural network (CNN) --- deep metric learning --- multi-task learning --- image classification --- age estimation --- generative adversarial network --- emotion classification --- facial key point detection --- facial images processing --- convolutional neural networks --- face liveness detection --- convolutional neural network --- thermal image --- external knowledge

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Intelligent optimization is based on the mechanism of computational intelligence to refine a suitable feature model, design an effective optimization algorithm, and then to obtain an optimal or satisfactory solution to a complex problem. Intelligent algorithms are key tools to ensure global optimization quality, fast optimization efficiency and robust optimization performance. Intelligent optimization algorithms have been studied by many researchers, leading to improvements in the performance of algorithms such as the evolutionary algorithm, whale optimization algorithm, differential evolution algorithm, and particle swarm optimization. Studies in this arena have also resulted in breakthroughs in solving complex problems including the green shop scheduling problem, the severe nonlinear problem in one-dimensional geodesic electromagnetic inversion, error and bug finding problem in software, the 0-1 backpack problem, traveler problem, and logistics distribution center siting problem. The editors are confident that this book can open a new avenue for further improvement and discoveries in the area of intelligent algorithms. The book is a valuable resource for researchers interested in understanding the principles and design of intelligent algorithms.

Technology: general issues --- global optimization --- cuckoo search algorithm --- Q-learning --- mutation --- self-adaptive step size --- evolutionary computation --- playtesting --- game feature --- game simulation --- game trees --- playtesting metric --- validation --- Pareto optimality --- h-index --- ranking --- dominance --- Pareto-front --- multi-indicators --- multi-metric --- multi-resources --- citation --- universities ranking --- swarm intelligence --- simulated annealing --- krill herd --- particle swarm optimization --- quantum --- elephant herding optimization --- engineering optimization --- metaheuristic --- constrained optimization --- multi-objective optimization --- single objective optimization --- differential evolution --- success-history --- premature convergence --- turning-based mutation --- opposition-based learning --- ant colony optimization --- opposite path --- traveling salesman problems --- whale optimization algorithm --- WOA --- binary whale optimization algorithm --- bWOA-S --- bWOA-V --- feature selection --- classification --- dimensionality reduction --- menu planning problem --- evolutionary algorithm --- decomposition-based multi-objective optimisation --- memetic algorithm --- iterated local search --- diversity preservation --- single-objective optimization --- knapsack problem --- travelling salesman problem --- seed schedule --- many-objective optimization --- fuzzing --- bug detection --- path discovery --- evolutionary algorithms (EAs) --- coevolution --- dynamic learning --- performance indicators --- magnetotelluric --- one-dimensional inversions --- geoelectric model --- optimization problem --- multi-task optimization --- multi-task evolutionary computation --- knowledge transfer --- assortative mating --- unified search space --- quantum computing --- grey wolf optimizer --- 0-1 knapsack problem --- green shop scheduling --- fuzzy hybrid flow shop scheduling --- discrete artificial bee colony algorithm --- minimize makespan --- minimize total energy consumption

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Intelligent optimization is based on the mechanism of computational intelligence to refine a suitable feature model, design an effective optimization algorithm, and then to obtain an optimal or satisfactory solution to a complex problem. Intelligent algorithms are key tools to ensure global optimization quality, fast optimization efficiency and robust optimization performance. Intelligent optimization algorithms have been studied by many researchers, leading to improvements in the performance of algorithms such as the evolutionary algorithm, whale optimization algorithm, differential evolution algorithm, and particle swarm optimization. Studies in this arena have also resulted in breakthroughs in solving complex problems including the green shop scheduling problem, the severe nonlinear problem in one-dimensional geodesic electromagnetic inversion, error and bug finding problem in software, the 0-1 backpack problem, traveler problem, and logistics distribution center siting problem. The editors are confident that this book can open a new avenue for further improvement and discoveries in the area of intelligent algorithms. The book is a valuable resource for researchers interested in understanding the principles and design of intelligent algorithms.

global optimization --- cuckoo search algorithm --- Q-learning --- mutation --- self-adaptive step size --- evolutionary computation --- playtesting --- game feature --- game simulation --- game trees --- playtesting metric --- validation --- Pareto optimality --- h-index --- ranking --- dominance --- Pareto-front --- multi-indicators --- multi-metric --- multi-resources --- citation --- universities ranking --- swarm intelligence --- simulated annealing --- krill herd --- particle swarm optimization --- quantum --- elephant herding optimization --- engineering optimization --- metaheuristic --- constrained optimization --- multi-objective optimization --- single objective optimization --- differential evolution --- success-history --- premature convergence --- turning-based mutation --- opposition-based learning --- ant colony optimization --- opposite path --- traveling salesman problems --- whale optimization algorithm --- WOA --- binary whale optimization algorithm --- bWOA-S --- bWOA-V --- feature selection --- classification --- dimensionality reduction --- menu planning problem --- evolutionary algorithm --- decomposition-based multi-objective optimisation --- memetic algorithm --- iterated local search --- diversity preservation --- single-objective optimization --- knapsack problem --- travelling salesman problem --- seed schedule --- many-objective optimization --- fuzzing --- bug detection --- path discovery --- evolutionary algorithms (EAs) --- coevolution --- dynamic learning --- performance indicators --- magnetotelluric --- one-dimensional inversions --- geoelectric model --- optimization problem --- multi-task optimization --- multi-task evolutionary computation --- knowledge transfer --- assortative mating --- unified search space --- quantum computing --- grey wolf optimizer --- 0-1 knapsack problem --- green shop scheduling --- fuzzy hybrid flow shop scheduling --- discrete artificial bee colony algorithm --- minimize makespan --- minimize total energy consumption

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Connected and automated vehicles (CAVs) are a transformative technology that is expected to change and improve the safety and efficiency of mobility. As the main functional components of CAVs, advanced sensing technologies and control algorithms, which gather environmental information, process data, and control vehicle motion, are of great importance. The development of novel sensing technologies for CAVs has become a hotspot in recent years. Thanks to improved sensing technologies, CAVs are able to interpret sensory information to further detect obstacles, localize their positions, navigate themselves, and interact with other surrounding vehicles in the dynamic environment. Furthermore, leveraging computer vision and other sensing methods, in-cabin humans’ body activities, facial emotions, and even mental states can also be recognized. Therefore, the aim of this Special Issue has been to gather contributions that illustrate the interest in the sensing and control of CAVs.

Technology: general issues --- History of engineering & technology --- TROOP --- truck platooning --- path planning --- kalman filter --- V2V communication --- string stability --- off-tracking --- articulated cargo trucks --- kabsch algorithm --- potential field --- sigmoid curve --- autonomous vehicles --- connected and autonomous vehicles --- artificial neural networks --- end-to-end learning --- multi-task learning --- urban vehicle platooning --- simulation --- attention --- executive control --- simulated driving --- task-cuing experiment --- electroencephalogram --- fronto-parietal network --- object vehicle estimation --- radar accuracy --- data-driven --- radar latency --- weighted interpolation --- autonomous vehicle --- urban platooning --- vehicle-to-vehicle communication --- in-vehicle network --- analytic hierarchy architecture --- traffic scenes --- object detection --- multi-scale channel attention --- attention feature fusion --- collision warning system --- ultra-wideband --- dead reckoning --- time to collision --- vehicle dynamic parameters --- Unscented Kalman Filter --- multiple-model --- electric vehicle --- unified chassis control --- unsprung mass --- autonomous driving --- trajectory tracking --- real-time control --- model predictive control --- tyre blow-out --- yaw stability --- roll stability --- vehicle dynamics model --- n/a