Machine learning is increasingly becoming a major engine of economic growth in technologically advanced countries across the world. This phenomenon is manifested by the explosively growing variety and diversity of industrial applications and products incorporating machine learning technologies. However, a number of fundamental challenges are beginning to emerge that could potentially slow the growth of this vital technology, the most significant of which is the transfer learning problem: how to take training data from one domain or task and apply it in a new context?
This tutorial provides a unified framework that reviews recent work on transfer learning, centered around two mathematical themes of maximizing correlations and exploiting symmetries. A range of real-world examples, from image recognition, cross-lingual information retrieval, natural language processing, and reinforcement learning will be used to illustrate the techniques.

1. • Introduction and Historical Motivation: 4:00-4:20 p.m.
   

2. • Mathematical Preliminaries : 4:20-4:40 p.m.
   

3. • Algorithms for Transfer Learning: 4:40-5:10 p.m.
   

4. • Applications of Transfer Learning: 5:10-5:45 p.m.