Open World Learning

This book provides state-of-the-art contemporary research insights into key applications and processes in open world learning. Open world learning seeks to understand access to education, structures, and the presence of dialogue and support systems. It explores how the application of open world and educational technologies can be used to create opportunities for open and high-quality education. Presenting ground-breaking research from an award winning Leverhulme doctoral training programme, the book provides several integrated and cohesive perspectives of the affordances and limitations of open world learning. The chapters feature a wide range of open world learning topics, ranging from theoretical and methodological discussions to empirical demonstrations of how open world learning can be effectively implemented, evaluated, and used to inform theory and practice. The book brings together a range of innovative uses of technology and practice in open world learning from 387,134 learners and educators learning and working in 136 unique learning contexts across the globe and considers the enablers and disablers of openness in learning, ethical and privacy implications, and how open world learning can be used to foster inclusive approaches to learning across educational sectors, disciplines and countries. The book is unique in exploring the complex, contradictory and multi-disciplinary nature of open world learning at an international level and will be of great interest to academics, researchers, professionals, and policy makers in the field of education technology, e-learning and digital education. The Open Access version of this book, available at www.taylorfrancis.com, has been made available under a Creative Commons Attribution-Non Commercial-No Derivatives 4.0 license.

Advances in Computers, Volume presents innovations in computer hardware, software, theory, design and applications, with this updated volume including new chapters on Contains novel subject matter that is relevant to computer science Includes the expertise of contributing authors Presents an easy to comprehend writing style

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.

The Internet and associated technologies have been around for almost twenty years. Networked access and computer ownership are now the norm. There is a plethora of technologies that can be used to support learning, offering different ways in which learners can communicate with each other and their tutors, and providing them with access to interactive, multimedia content. However, these generic skills don’t necessarily translate seamlessly to an academic learning context. Appropriation of these technologies for academic purposes requires specific skills, which means that the way in which we design and support learning opportunities needs to provide appropriate support to harness the potential of technologies. More than ever before learners need supportive ‘learning pathways’ to enable them to blend formal educational offerings, with free resources and services. This requires a rethinking of the design process, to enable teachers to take account of a blended learning context.

This book introduces the new paradigm of lifelong and continual learning dialogue systems to endow dialogue systems with the ability to learn continually by themselves through their own self-initiated interactions with their users and the working environments. The authors present the latest developments and techniques for building such continual learning dialogue systems. The book explains how these developments allow systems to continuously learn new language expressions, lexical and factual knowledge, and conversational skills through interactions and dialogues. Additionally, the book covers techniques to acquire new training examples for learning new tasks during the conversation. The book also reviews existing work on lifelong learning and discusses areas for future research.

This book constitutes the refereed proceedings of the 14th International Conference on Multi-disciplinary Trends in Artificial Intelligence, MIWAI 2021, held online in July 2021. The 13 full papers and 3 short papers presented were carefully reviewed and selected from 33 submissions. They cover a wide range of topics in theory, methods, and tools in AI sub-areas such as cognitive science, computational philosophy, computational intelligence, game theory, machine learning, multi-agent systems, natural language, representation and reasoning, data mining, speech, computer vision and the Web as well as their applications in big data, bioinformatics, biometrics, decision support, knowledge management, privacy, recommender systems, security, software engineering, spam filtering, surveillance, telecommunications, Web services, and IoT.

Lifelong Machine Learning (or Lifelong Learning) is an advanced machine learning paradigm that learns continuously, accumulates the knowledge learned in previous tasks, and uses it to help future learning. In the process, the learner becomes more and more knowledgeable and effective at learning. This learning ability is one of the hallmarks of human intelligence. However, 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. It makes no attempt to retain the learned knowledge and use it in future learning. Although this isolated learning paradigm has been very successful, it requires a large number of training examples, and is only suitable for well-defined and narrow tasks. In comparison, we humans can learn effectively with a few examples because we have accumulated so much knowledge in the past which enables us to learn with little data or effort. Lifelong learning aims to achieve this capability. As statistical machine learning matures, it is time to make a major effort to break the isolated learning tradition and to study lifelong learning to bring machine learning to new heights. Applications such as intelligent assistants, chatbots, and physical robots that interact with humans and systems in real-life environments are also calling for such lifelong learning capabilities. Without the ability to accumulate the learned knowledge and use it to learn more knowledge incrementally, a system will probably never be truly intelligent. This book serves as an introductory text and survey to lifelong learning.