November 13, 2020
EE 399: Probability Models and Inference for Engineering (4 credits)
Instructor: Sreeram Kannan
Lecture:
EE 399A (SLN 13605): Wed/Fri 1:00 – 2:20
Quiz Sections:
EE 399AA (SLN 13606): Tue 9:30 – 11:20
EE 499AB (SLN 13607): Wed 9:30 – 11:20
EE 399AC (SLN 13608): Fri 3:30 – 5:20
Prerequisite: Math 126
Description: This course introduces probabilistic concepts in conjunction with statistical computation methods. The course draws examples and motivations from applications throughout Electrical and Computer Engineering, with topics including reliability, system engineering, engineering decision-making, and parameter estimation. The accompanying labs apply concepts and develop skills for modeling and inference from probabilistic data sets.
This course can be used for satisfying the EE undergrad requirement in Probability and Statistics.
Learning Objectives: At the conclusion of the course, the student will
a. Understand basic axioms of probability and how to compute relevant statistics
b. Be familiar with basic discrete and continuous random variables
c. Be able to map engineering problems to appropriate probabilistic models
d. Be proficient with fundamental data processing principles
e. Be able to conduct statistical simulation experiments well as
write simple inference algorithms
Topics
1. Foundations of Probability
Sample space, probability, independence, counting
2. Discrete Random Variables
Probability mass functions, functions of random variables, expectation, joint PMF, conditioning, independence
3. Continuous Random Variables
Probability density function and cumulative distribution functions, Gaussian, Possion random variables, Conditioning, multiple variables
4. Further topics
Bivariate Random variables: Covariance, correlation, Inference, Model fitting
Books
1. Introduction to Probability, Bertsekas and Tsitsiklis
Solutions manual available online: http://athenasc.com/prob-solved_2ndedition.pdf (Links to an external site.)
2. Probability with Engineering applicaitons, Bruce Hajek (UIUC notes): https://courses.engr.illinois.edu/ece313/sp2019/notes_webpage.html (Links to an external site.)
3. (Labs) Think Stats: Probability and Statistics for Programmers ( http://www.greenteapress.com/thinkstats/html/index.html (Links to an external site.))
Sources for problem solving
1. Textbook problems in “Introduction to Probability, Bertsekas and Tsitsiklis”
Solutions manual available online: http://athenasc.com/prob-solved_2ndedition.pdf (Links to an external site.)
2. There are problems with worked out video solutions in
https://courses.engr.illinois.edu/ece313/sp2019/notes_webpage.html (Links to an external site.)
Search for [Video] in the book above. Example here: https://uofi.app.box.com/s/yeogfk614ziroxx9bzjk (Links to an external site.)
Labs
There will be accompanying probability labs that emphasize Monte Carlo simulations as well as performing inference using real data in Python. It will be based partly on the Think Stats book referred here.
Grading
Homeworks – 4 (theory) + 4 (simulation) – 40%
Midterm – 20%
Final – 25%
Class participation – 5%
Quizzes – 10%
Quiz: 15-minute quiz asking brief questions