Frontiers in brain-inspired AI (2017 Spring Bis800)
This course will explore frontiers in modern brain-inspired artificial intelligence. The first part of our course discusses key topics in machine learning - statistical learning theory, support vector machines, kernel machines, generative models, and deep learning algorithms. The second part focuses on reinforcement learning; students are expected to learn about theory, algorithms, and most importantly how reinforcement learning control is implemented in the human brain. We will also discuss recent advances in deep reinforcement learning.
Rm.#205 (E16-1 YangBoonSoon B/D)
MON and WED 10:30-11:50 AM
Sang Wan Lee (email@example.com, Rm.#516 E16-1)
Tuesday and Thursdays 11 AM – noon
Jun Yeol Kim, Jung Bae Park
3 units (3:0:0).
None. Calculus, linear algebra, and probability should be sufficient.
Attendance (30%), term projects (40%), presentation (30%)
Attending the majority of the lectures is important (30%). During the midterm exam week, you will need to carry out a simple program assignment (30%) for which you can work out a problem in context within the field you are working on. In the final presentation (40%), you should choose one journal article from a given list (announced after the midterm), and then give an oral presentation to discuss the questions the paper addresses and to provide a critique.
Lecture materials (70%) + a few chapters of the followings (30%):
- R. S. Sutton and A. G. Barto, An Introduction to Reinforcement Learning, MIT Press, 1998.
- D. Bertsekas, Dynamic Programming and Optimal Control: Approximate dynamic
programming (Volume 2), Athena Scientific, 2012.