Originally published in 1976, this title is an edited volume and reflects the major approaches being taken in structural learning at the time. Chapter 1 deals with the basic question of whether competence (knowledge) should be characterized in terms of rules (automata), on the one hand, or associations on the other. The bulk of Chapter 2 is devoted to a series of earlier experiments on rule learning by the editor and his associates. The two contributions in Chapter 3 deal with graph theoretical models. Piagetian models constitute the subject of Chapter 4. Chapter 5 deals with attempts to stimulate human behaviour with a computer. Chapter 6 ranges over a wide variety of competence models, with particular reference to logic and mathematics. In Chapter 7 the editor proposes a new theory of structural learning, together with some empirical results.

Originally published in 1973, this book was published in two volumes. In the first volume, the author describes what he sees as the rudiments of three deterministic partial theories of structural learning. The first involves competence, partial theories which deal only with the problem of how to account for the various kinds of behavior of which people are typically capable. Special attention is given to mathematical competence. Nothing is said about learning or performance. The second partial theory is concerned with motivation, learning, and performance under idealized conditions, and is obtained from the first partial theory by imposing further structure on it. This theory says nothing about memory of the limited capacity of human subjects to process information. ... The final theory is obtained from the second by making additional assumptions, which bring memory and finite information processing into the picture. The theory is still partial, however, since no attempt is made to deal with certain ultra-short-term behavioral phenomena which appear to depend directly on particular physiological characteristics.

Instructional Design Theories and Models is a thorough yet concise overview of eight of the most comprehensive and best-known attempts to integrate knowledge about effective and appealing instruction. Chapters were written by the original theorists to provide a more accurate and behind-the-scenes look at the theories' development. Instructional Des

Deep Learning models are at the core of artificial intelligence research today. It is well known that deep learning techniques are disruptive for Euclidean data, such as images or sequence data, and not immediately applicable to graph-structured data such as text. This gap has driven a wave of research for deep learning on graphs, including graph representation learning, graph generation, and graph classification. The new neural network architectures on graph-structured data (graph neural networks, GNNs in short) have performed remarkably on these tasks, demonstrated by applications in social networks, bioinformatics, and medical informatics. Despite these successes, GNNs still face many challenges ranging from the foundational methodologies to the theoretical understandings of the power of the graph representation learning. This book provides a comprehensive introduction of GNNs. It first discusses the goals of graph representation learning and then reviews the history, current developments, and future directions of GNNs. The second part presents and reviews fundamental methods and theories concerning GNNs while the third part describes various frontiers that are built on the GNNs. The book concludes with an overview of recent developments in a number of applications using GNNs. This book is suitable for a wide audience including undergraduate and graduate students, postdoctoral researchers, professors and lecturers, as well as industrial and government practitioners who are new to this area or who already have some basic background but want to learn more about advanced and promising techniques and applications.

One outcome of recent progress in educational technology is strong interest in providing effective support for learning in complex and ill-structured domains. We know how to use technology to promote understanding in simpler domains (e.g., orientation information, procedures with minimal-branching, etc.), but we are less sure how to use technology to support understanding in more complex domains (e.g., managing limited resources, understanding environmental impacts, etc.). Such domains are increasingly significant for society. Technology (e.g., collaborative tele-learning, digital repositories, interactive simulations, etc.) can provide conceptually and functionally rich domains for learning. However, this introduces the problem of determining what works in which circumstances and why. Research and development on these matters is reflected in this collection of papers. This research suggests a need to rethink foundational issues in educational philosophy and learning technology. One major theme connecting these papers is the need to address learning in the large - from a more holistic perspective. A second theme concerns the need to take learners where and as they are, integrating technology into effective learning places. Significant and systematic progress in learning support for complex domains demands further attention to these important issues.

Adult education has never been more important or urgent than it is today Few educators have had the impact on adult education of Griff Foley. Professor Peter McLaren, University of California, Los Angeles This timely and valuable book makes an important contribution to our understanding of key recent developments in adult education and their significance. Reflecting the increasingly global nature of scholarship in the field, well-respected international contributors analyse issues facing practitioners today, and consider how these can be most positively embraced to further the international cause of adult learning and social justice. Janet Hannah, University of Nottingham Learning is central to all aspects of human life, and failure to learn brings dire consequences. As our world becomes more integrated and complex, adult learning has become more important. Dimensions of Adult Learning offers a broad overview of adult learning in the workplace and community. Written by a team of international experts, it introduces the core skills and knowledge which underpin effective practice. It examines adult education policy and research, and highlights the social nature of adult learning. It also examines adult learning in different contexts: on-line learning, problem-based learning, organisational and vocational learning. Dimensions of Adult Learning is an essential reference for professionals and students. Griff Foley is Research Associate in Adult Education at the University of Technology, Sydney. He is author of Learning in Social Action and Strategic Learning.