A Survey on Transfer Learning

PhD Qualifying Examination


Title: "A Survey on Transfer Learning"

by

Mr. Wenyuan DAI


Abstract:

Transfer learning is known as learning one area by the help from another area. 
It obeys the basic assumption of traditional machine learning (PAC learning), 
which requires the underlying distribution of the training data should be the 
same as the one of test data. Transfer learning is important because some areas 
do not have so many data, such as medical diseases. Based on transfer 
learn-ing, we can do ??small data?? machine learning by the help of large 
amount of data from related area. In this survey, we will briefly introduce the 
history of transfer learning research, and divided transfer learning problem 
into three di-rections. In each direction, we will go through all the previous 
related work. Finally, we will show some transfer learning applications in 
industry, and the discuss some future works.


Date:			Thursday, 31 August 2017

Time:                  	3:00pm - 5:00pm

Venue:                  Room 2612A
                         Lifts 31/32

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


**** ALL are Welcome ****