Concept formation knowledge and experience in unsupervised learning

摘要: Concept formation lies at the center of learning and cognition. Unlike much work in machine cognitive psychology, research on this topic focuses unsupervised incremental acquisition conceptual knowledge. Recent concept addresses a number important issues. Foremost among these are principles similarity that guide retrieval human machine, including contribution surface features, goals, `deep' features. Another active area explores mechanisms for efficiently reorganizing memory response to ongoing experiences confront intelligent agents. Finally, methods play an increasing role problem solving planning, developmental engineering applications, constructive induction. This book brings together results from psychology learning, explanation-based inductive approaches. Chapters differing perspectives intermingled highlight commonality their agendas. In addition scientists AI researchers, will interest data analysts involved clustering, philosophers concerned with nature origin concepts, any researcher dealing issues similarity, organization, solving.