An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
Abstract
Since about 100 years ago, to learn the intrinsic structure of data, many representation learning approaches have been proposed, including both linear ones and nonlinear ones, supervised ones and unsupervised ones. Particularly, deep architectures are widely applied for representation learning in recent years, and have delivered top results in many tasks, such as image classification, object detection and speech recognition. In this paper, we review the development of data representation learning methods. Specifically, we investigate both traditional feature learning algorithms and state-of-the-art deep learning models. The history of data representation learning is introduced, while available resources (e.g. online course, tutorial and book information) and toolboxes are provided. Finally, we conclude this paper with remarks and some interesting research directions on data representation learning.
Cite
@article{arxiv.1611.08331,
title = {An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning},
author = {Guoqiang Zhong and Li-Na Wang and Junyu Dong},
journal= {arXiv preprint arXiv:1611.08331},
year = {2016}
}
Comments
About 20 pages. Submitted to Journal of Finance and Data Science as an invited paper