Welcome to Transfer Learning


Description: A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. For example, we sometimes have a classification task in one domain of interest, but we only have sufficient training data in another domain of interest, where the latter data may be in a different feature space or follow a different data distribution. In such cases, knowledge transfer, if done successfully, would greatly improve the performance of learning by avoiding much expensive data labeling efforts. In recent years, transfer learning has emerged as a new learning framework to address this problem. This course focuses on categorizing and reviewing the current progress on transfer learning for classification, regression and clustering problems. We discuss the relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as co-variate shift. We also explore some potential future issues in transfer learning research.

 

Organizer: Associate Professor Bin Yang, e-mail: byang@cs.aau.dk

Lecturers: (TBC) Assistant Professor Sinno Jialin Pan, Nanyang Technological University

ECTS: 2

Time: Fall 2018

Place: Aalborg University

Zip code: 9220

City: Aalborg Øst

Number of seats: 30

Deadline: 20 April 2018

Important information concerning PhD courses We have over some time experienced problems with no-show for both project and general courses. It has now reached a point where we are forced to take action. Therefore, the Doctoral School has decided to introduce a no-show fee of DKK 5,000 for each course where the student does not show up. Cancellations are accepted no later than 2 weeks before start of the course. Registered illness is of course an acceptable reason for not showing up on those days. Furthermore, all courses open for registration approximately three months before start. This can hopefully also provide new students a chance to register for courses during the year. We look forward to your registrations.