New approaches for heterogeneous transfer learning
In many real-world problems, it is often time-consuming and expensive to collect labeled data. To alleviate this challenge, transfer learning (TL) techniques that adapt a model from a related task with ample labeled data to a task of interest with little or no additional human supervision have been...
Main Author: | Zhou, Tianyi |
---|---|
Other Authors: | Tsang Wai-Hung, Ivor |
Format: | Thesis |
Language: | English |
Published: |
2015
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/65532 |
Similar Items
-
Car detection using transfer learning methodology
by: Mundhra, Shreyas Sudhir
Published: (2017) -
Transfer learning for visual recognition and text categorization
by: Duan, Lixin
Published: (2012) -
Multi-view positive and unlabeled learning
by: Zhou, Joey Tianyi, et al.
Published: (2014) -
Co-labeling : a new multi-view learning approach for ambiguous problems
by: Duan, Lixin, et al.
Published: (2013) -
Evolutionary transfer learning for complex multi-agent reinforcement learning systems
by: Hou, Yaqing
Published: (2017)