ECE 8528: Advanced Topics in Statistical Modeling
for Engineering Applications
Syllabus
Contact Information:

Lecture	TBD     TBD
Lecturer	Joseph Picone, Professor     Office: EA 703A     Office Hours: (MWF) 11:00 - 12:00 PM     Phone: 215-204-4841     Email: picone@temple.edu     Skype: joseph.picone
Social Media	temple.engineering.ece8528@groups.facebook.com
Website	http://www.isip.piconepress.edu/courses/temple/ece_8528
Required Textbook	None
Reference Textbooks	C.M. Bishop     Pattern Recognition and Machine Learning     Springer, ISBN: 978-0387310732, 2003.     D.J.C. MacKay     Information Theory, Inference and Learning Algorithms     Cambridge University Press, ISBN: 978-0521642989, 2004.   R.J. Thibaux   Nonparametric Bayesian Models For Machine Learning     Proquest, ISBN: 978-1243992130, 2011. Also, see the course web site for additional reading materials.
Prerequisites	ENGR 5022 (minimum grade: B-)   ENGR 5033 (minimum grade: B-)

Grading Policies:

Item	Weight
Exam No. 1	20%
Exam No. 2	20%
Exam No. 3	20%
Final Exam	20%
Project	20%
TOTAL:	100%

This course builds on a basic knowledge of machine learning and reviews recent advances in the field. It is a research-oriented course intended to complement a student's thesis or dissertation research. The course will focus on a selection of emerging machine learning algorithms and analyze contemporary publications on these techniques. The emphasis will be on algorithms suited to large, complex data sets. Both supervised and unsupervised learning methodologies will be discussed. Applications will be drawn from several signal processing disciplines including speech, image and bioengineering applications.

It is understood that the specific topic list in this course will evolve as new methods emerge. Currently, two topics that will be emphasized are nonparametric Bayesian methods and deep learning.

The course requirements include three in-class exams and a final exam. In addition, students will be expected to complete a course project that involves application of an existing contemporary statistical modeling approach to a real-world problem. Students are encouraged to draw on examples from their own research. The specifics of this assignment will be negotiated in writing with the course instructor, and fully defined by the fifth week of the course.

Lecture Schedule:

The lecture component will cover the following topics:

Class	Topic(s)
1	(a) Course Overview and Introduction     (b) Parametric Statistical Models     (c) The Expectation Maximization Algorithm
2	(a) Maximum Likelhood Approaches     (b) Discriminative Training     (c) Crossvalidation, Bagging and Jackknifing
3	(a) Nonparametric Bayesian Approaches     (b) Inference Algorithms     (c) Hybrid Models and Temporal Structure
4	(a) Deep Learning     (b) Random Fields and Bayesian Networks     (c) Deep Belief Networks
5	(a) Dimensionaltiy Reduction     (b) Kernel Theory     (c) Exam No. 1
6	(a) Variational Methods     (b) Variational EM     (c) Monte Carlo Methods
7	(a) Graphical Models     (b) Latent Semantic Analysis     (c) Social Network Analysis
8	(a) Statistical Learning Theory     (b) Fisher Information     (c) Bounds and Frequentist Theory
9	(a) Gaussian Processes     (b) Dirichlet Process Mixture Models     (c) Exam No. 2
10	(a) Supervised Learning     (b) Unsupervised Learning     (c) Adaptation
11	(a) Sparsity     (b) Greedy Algorithms     (c) Compression Sensing
12	(a) Online Learning     (b) Active Learning     (c) Nonparametric Learning
13	(a) Learning with Humans in the Loop     (b) Prediction of Complex Data     (c) Exam No. 3
14	(a) Applications: Search Engines     (b) Applications: Speech Recognition     (c) Applications: Predicting User Preferences (Netflix)
15	(a) Final Exam

Please note that the dates above are fixed since they have been arranged to optimize a number of constraints. You need to adjust your schedules, including job interviews and site visits, accordingly.