Lower the Barrier of Machine Learning: Meta Learning for Transfer Learning and AutoML

PhD Thesis Proposal Defence


Title: "Lower the Barrier of Machine Learning: Meta Learning for
Transfer Learning and AutoML"

by

Mr. Wenyuan DAI


Abstract:

Recent years, machine learning becomes the main methodology to develop 
artificial intelligence technology. However, traditional machine learning 
may face to three barriers: lack of data, poor feature quality, and less 
data scientists. In this thesis, we focus on how to lower the barrier of 
machine learning. We propose to use meta learning methodology to solve 
these problems. Specifically, meta learning can be applied to improve 
machine learning performance in transfer learning and AutoML scenarios, 
and lower the three main barriers correspondingly. We designed several new 
algorithms to solve the data, feature and model tuning problems, and 
showed advantages on many empirical studies.


Date:			Tuesday, 10 September 2019

Time:                  	2:00pm - 4:00pm

Venue:                  Room 5501
                         lifts 25/26

Committee Members:	Prof. Qiang Yang (Supervisor)
 			Dr. Yangqiu Song (Chairperson)
 			Dr. Kai Chen
 			Dr. Qifeng Chen


**** ALL are Welcome ****