Alexandria Digital Research Library

Representation learning on unstructured data

Author:
Han, Fangqiu
Degree Grantor:
University of California, Santa Barbara. Computer Science
Degree Supervisor:
Xifeng Yan
Place of Publication:
[Santa Barbara, Calif.]
Publisher:
University of California, Santa Barbara
Creation Date:
2016
Issued Date:
2016
Topics:
Computer science
Keywords:
Graph
Representation Learning
Machine Learning
Genres:
Online resources and Dissertations, Academic
Dissertation:
Ph.D.--University of California, Santa Barbara, 2016
Description:

Representation learning, which transfers real world data such as graphs, images and texts, into representations that can be effectively processed by machine learning algorithms, has became a new focus in machine learning community. Traditional machine learning algorithms usually focus on modeling hand-crafted feature representations manually extracted from the raw data and performance of the model highly depends on the quality of the data representation. However, feature engineering is laborious, hardly accurate, and less generalizable. Thus the weakness of many current learning algorithms is not how well they can model the data, but how good their input data representation are.

In this thesis, we adopt learning algorithms both on representing and modeling the graph data in two different applications. In the first work, We first developed representation on nodes, and later apply a well-known VG kernel on this representation. In the second work, we show the power of representation captured by applying jointly optimization on the nodes representations and the model. The results of both work show significant improvement over traditional machine learning methods.

Physical Description:
1 online resource (90 pages)
Format:
Text
Collection(s):
UCSB electronic theses and dissertations
ARK:
ark:/48907/f3qr4x85
ISBN:
9781369575736
Catalog System Number:
990047511880203776
Rights:
Inc.icon only.dark In Copyright
Copyright Holder:
Fangqiu Han
File Description
Access: Public access
Han_ucsb_0035D_13218.pdf pdf (Portable Document Format)