Transfer Learning from Unlabeled Data via Neural Networks

Authors:
Huaxiang Zhang;Hua Ji;Xiaoqin Wang
Affiliations:
Department of Computer Science, Shandong Normal University, Jinan, China 250014 and Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology, Jinan, China;Department of Computer Science, Shandong Normal University, Jinan, China 250014;Department of Computer Science, Shandong Normal University, Jinan, China 250014
Venue:
Neural Processing Letters
Year:
2012

Citing 9
Cited 0

A Bayesian/Information Theoretic Model of Learning to Learn viaMultiple Task Sampling

Machine Learning - Special issue on inductive transfer
Multi-task feature and kernel selection for SVMs

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Identifying Semantically Equivalent Object Fragments

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
One-Shot Learning of Object Categories

IEEE Transactions on Pattern Analysis and Machine Intelligence
Constructing informative priors using transfer learning

ICML '06 Proceedings of the 23rd international conference on Machine learning
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data

The Journal of Machine Learning Research
Sharing Visual Features for Multiclass and Multiview Object Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Self-taught learning: transfer learning from unlabeled data

Proceedings of the 24th international conference on Machine learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

A machine learning framework which uses unlabeled data from a related task domain in supervised classification tasks is described. The unlabeled data come from related domains, which share the same class labels or generative distribution as the labeled data. Patterns in the unlabeled data are learned via a neural network and transferred to the target domain from where the labeled data are generated, so as to improve the performance of the supervised learning task. We call this approach self-taught transfer learning from unlabeled data. We introduce a general-purpose feature learning algorithm producing features that retain information from the unlabeled data. Information preservation assures that the features obtained will be useful for improving the classification performance of the supervised tasks.