Transfer learning through embedding spaces / Mohammad Rostami.
| Author/creator | Rostami, Mohammed |
| Format | Electronic |
| Edition | First edition. |
| Publication Info | Boca Raton : CRC Press, Taylor & Francis Group, 2021. |
| Description | xxi, 198 pages : illustrations ; 27 cm |
| Supplemental Content | Full 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 note | Based on author's thesis (Ph. D.)--University of Pennsylvania, 2019, entitled: Learning transferable knowledge through embedding spaces. |
| Bibliography note | Includes bibliographical references (pages 173-195) and index. |
| Access restriction | Available only to authorized users. |
| Technical details | Mode of access: World Wide Web |
| Genre/form | Electronic books. |
| LCCN | 2021002745 |
| ISBN | 9780367699055 (hbk) |
| ISBN | (ebk) |