Transfer learning through embedding spaces / Mohammad Rostami.

Author/creator Rostami, Mohammed
Format Electronic
EditionFirst edition.
Publication InfoBoca Raton : CRC Press, Taylor & Francis Group, 2021.
Descriptionxxi, 198 pages : illustrations ; 27 cm
Supplemental ContentFull text available from Taylor & Francis eBooks
Subjects

Abstract "In this book, we provide a brief background on transfer learning and then focus on the idea of transferring knowledge through intermediate embedding spaces. The idea is to couple and relate different learning through embedding spaces that encode task-level relations and similarities. We cover various machine learning scenarios and demonstrate that this idea can be used to overcome challenges of zero-shot learning, few-shot learning, domain adaptation, continual learning, lifelong learning, and collaborative learning"-- Provided by publisher.
General noteBased on author's thesis (Ph. D.)--University of Pennsylvania, 2019, entitled: Learning transferable knowledge through embedding spaces.
Bibliography noteIncludes bibliographical references (pages 173-195) and index.
Access restrictionAvailable only to authorized users.
Technical detailsMode of access: World Wide Web
Genre/formElectronic books.
LCCN 2021002745
ISBN9780367699055 (hbk)
ISBN(ebk)