Includes bibliographical references (pages [336]-376) and index.
Contents:
Transfer learning in urban computing. Feature-based transfer learning -- Model-based transfer learning -- Relation-based transfer learning -- Heterogeneous transfer learning -- Adversarial transfer learning -- Transfer learning in reinforcement learning -- Multi-task learning -- Transfer learning theory -- Transitive transfer learning -- AutoTL : learning to transfer automatically -- Few-shot learning -- Lifelong machine learning -- Privacy-preserving transfer learning -- Transfer learning in computer vision -- Transfer learning in natural language processing -- Transfer learning in dialogue systems -- Transfer learning in recommender systems -- Transfer learning in bioinformatics -- Transfer learning in activity recognition -- Transfer learning in urban computing.
Summary:
"This book is about the foundations, methods, techniques and applications of transfer learning. Transfer learning deals with how learning systems can quickly adapt themselves to new situations, new tasks and new environments. Transfer learning is a particularly important area of machine learning, which we can understand from several angles. First, the ability to learn from small data seems to be a particularly strong aspect of human intelligence. For example, we observe that babies learn from only a few examples and can quickly and effectively generalize from the few examples to concepts. This ability to learn from small data can be partly explained by the ability of humans to leverage and adapt the previous experience and pre-trained models to help solve future target problems. Adaptation is an innate ability of intelligent beings and artificially intelligent agents should certainly be endowed with transfer-learning ability"-- Provided by publisher.
This resource is supported by the Institute of Museum and Library Services under the provisions of the Library Services and Technology Act as administered by State Library of Iowa.