Probabilistic Graphical Models
639 Advanced Topics in Signal Processing and Communication
[Home] [Lectures] [Final Project]
For the final project, you are asked to provide a
survey study on one of the following topics in machine learning. For each
topic, I have selected two papers for you and you are required to add at least
three more to the list. The goals of the final project are for you
a. To summarize key ideas of an advanced or emerging
topic in machine learning
b. To provide a critical analysis for each paper based
on its strengths and weaknesses
c. To evaluate available software or demonstrate with
your own toy examples
d. To speculate important future research directions
and open questions on your chosen topic
e. To educate the rest of the class on this topic in an
Your grade will be based on a 0.5 hour in-class presentation (12/10 & 12/12) and
a final report (due 12/15) in double-column format with
at least 6 pages (MS-word
template or LaTeX template). The presentation will be judged by me,
Nikky and your peers. The quality of the report and
presentation will be graded based on the above criteria.
In order to learn as much as possible from each
other, I would like to have a different topic for each of you. Please send me
your order of preference of all the topics by 11/11 and I will make the final
topic assignment on 11/12 in class.
The topics and presenters are as follows:
Learning (Presenter: Qingguo Xu)
a. Y. Bengio, Learning deep
architectures for AI, Foundations and Trends in Machine Learning, vol. 2,
no. 1, pp. 1127, 2009.
b. A. Krizhevsky, I. Sutskever, and G. E. Hinton, ImageNet
classification with deep convolutional neural networks, in Advances
in Neural Information Processing Systems, 2012, pp. 10971105.
b. Hoffman, M., Bach, F. R., & Blei,
D. M. (2010). Online
learning for latent Dirichlet allocation. In
advances in neural information processing systems (pp. 856-864).
a. Gibson, B. R., Rogers, T. T., & Zhu, X. (2013). Human Semi‐Supervised
Learning. Topics in cognitive science, 5(1), 132-172.
b. Zhou, Z. H., & Li, M. (2010). Semi-supervised
learning by disagreement. Knowledge and Information Systems, 24(3),
a. Pan, S. J., & Yang, Q. (2010). A survey on
transfer learning. Knowledge and Data Engineering, IEEE Transactions on,
b. Long, M., Wang, J., Ding, G., Sun, J., & Yu, P.
S. (2013). Transfer
Feature Learning with Joint Distribution Adaptation. In Computer Vision
(ICCV), 2013 IEEE International Conference on (pp. 2200-2207). IEEE.
a. Seeger, M. (2004). Gaussian
processes for machine learning. International Journal of Neural Systems,
b. Wang, J. M., Fleet, D. J., & Hertzmann,
A. (2008). Gaussian
process dynamical models for human motion. Pattern Analysis and Machine
Intelligence, IEEE Transactions on, 30(2), 283-298.