Dual Learning: Algorithms and Applications
Speaker: Dr. Tao Qin
Microsoft Research Asia
Title: "Dual Learning: Algorithms and Applications"
Date: Wednesday, 7 March 2018
Time: 2:00pm - 3:00pm
Venue: Room 2303 (via lift 17/18), HKUST
In this talk, I will introduce the latest development of a new learning
paradigm: dual learning. While structural duality is common in AI, most
learning algorithms have not exploited it in learning/inference. Dual
learning is a new learning framework that leverages the primal-dual
structure of AI tasks to obtain effective feedback or regularization
signals to enhance the learning/inference process. I will first introduce
several dual learning algorithms: (1) dual unsupervised learning, (2) dual
supervised learning, (3) dual transfer learning, and (4) dual inference.
Then I will cover several applications, including neural machine
translation, image understanding, sentiment analysis, question
answering/generation, image translation, etc.
Dr. Tao Qin is a Senior Research Manager in Microsoft Research Asia. His
research interests include machine learning (with the focus on deep
learning and reinforcement learning), artificial intelligence (with
applications to language understanding and computer vision), game theory
and multi-agent systems (with applications to cloud computing, online and
mobile advertising, ecommerce), information retrieval and computational
advertising. He is an Adjunct Professor (PhD advisor) in the University of
Science and Technology of China.