Inductive Transfer

• Type: Chapter or Part of a Book
• Date: 2017

Authors

Ricardo Vilalta (Author) Other; Christophe Giraud-Carrier (Author) Other; Pavel Brazdil (Author) FEP; Carlos Soares (Author) FEUP

Book

Title: Encyclopedia of Machine Learning and Data Mining

Pages: 666-671

ISBN: 978-1-4899-7685-7

Electronic ISBN: 978-1-4899-7685-7

Other information

Authenticus ID: P-00M-NW6

DOI: 10.1007/978-1-4899-7687-1_138

Abstract (EN): We describe different scenarios where a learning mechanism is capable of acquiring experience on a source task, and subsequently exploit such experience on a target task. The core ideas behind this ability to transfer knowledge from one task to another have been studied in the machine learning literature under different titles and perspectives. Here we describe some of them under the names of inductive transfer, transfer learning, multitask learning, meta-searching, meta-generalization, and domain adaptation.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 7