Course Information and Administrivia
Announcements
- Aug. 5: Website Up and Running
- Aug. 6: Class Schedule Updated
- Aug. 25: Office hour will be held starting after the first lecture (No office hour on Aug 26)
- Aug. 29: Homework 0 Released
- Sep. 3: ICA 1 Released
- Sep. 5: MP 1 Part 1 Released
- Sep. 17 ICA 2 Released
- Sep. 19: HW 1 Released
- Sep. 24: MP 1 Part 2 Released
- Oct. 3: MP 1 Part 3 Released
- Oct. 8: ICA 4 (Practice Midterm) Released
Course Instructor
Ravishankar K Iyer, Professor, Electrical and Computer Engineering
- Office: 255 Coordinated Science Lab MC 228
- Email: rkiyer@illinois.edu
- Office Hours: Wed 4:00 – 5:00 PM in Person or Via Zoom, or by appointment, if necessary
Course CRN
- Undergrad – 3 hours – CRN: 77531 | Grad – 4 hours – CRN: 77533
Class Times
- Tuesday Thrusday 3:30 - 4:50 PM
Lecture Room
- ECEB 1015
Meeting Links
- Lecture, office hours, and discussion Zoom links will be posted on Campuswire
Campuswire (Class Discussion Board)
- Class discussions and announcements will be made on Campuswire, please join.
- Access code: 9079.
Grades & Homework Submission
- Homework should be submitted on Canvas
Lecture Recordings
- Lecture recordings are available on Mediaspace
Teaching Assistants
Shengkun Cui
- Email: scui8@illinois.edu
- Office Hours: Tuesday 5:00 - 6:00 PM CSL 240 in Person or Via Zoom, or by appointment, if necessary
Mosbah Aouad
- Email: maouad2@illinois.edu
- Office Hours: Thrusday 5:00 - 6:00 PM CSL 249 in Person or Via Zoom, or by appointment, if necessary
Yurui Cao
- Email: yuruic2@illinois.edu
- Office Hours: Wednesday 2:00 - 3:00 PM CSL 246 in Person or Via Zoom, or by appointment, if necessary
Administrivia
About the Class
This class will introduce students to real-world problems of societal importance (e.g., Safety of AVs, Health Analytics, Large-scale Infrastructures) and their solutions (using e.g., Bayesian networks, Factor Graphs, and large language models (LLMs)). The course will use real data from several domains (including resiliency and healthcare science) to instill in the students following data‐science and AI/ML expertise:
- Data: measurement and management
- Identifying key data characteristics
- Problem formulation, machine learning models and validation
- Design, construction, and assessment of end‐to‐end workflows
- Generating application domain insights that can improve the understanding of the problem in question
Through this course, students will be able to develop expertise and the ability to form intuitions which can be more broadly applicable. Such expertises will prepare students for data science and ML engineering roles.
Course Description
Many modern application domains require engineers and domain experts to collaborate in designing and analyzing complex datasets, often with the objective of automating the decision-making process (often referred to as inferring “actionable intelligence”). Combining the right data with science/domain knowledge and Machine Learning (ML) to generate actionable intelligence remains a compelling problem.
The course addresses this problem by allowing students to build analysis workflows that use advanced data measurement and management, combined with a variety of ML methods, ranging from Bayesian networks to large language models (LLMs) and their underlying principles. Students will work on real-world applications while interacting with invited domain experts. The course will instill the skillsets required for constructing end‐to‐end real‐world analysis workflows through lectures, in-class group activities, homework, and mini‐projects, which will allow students to derive domain insights. The course will use real‐world examples (measurement logs from supercomputers, data on autonomous vehicle safety, and clinical trials) together with ML methods ranging from Bayesian Networks to LLMs and their underlying principles.
Students will gain hands‐on implementation experience by completing two mini-projects requiring them to analyze high‐fidelity real‐world measurement data obtained from different application domains. While each workflow is end-to-end, the students will develop a deeper understanding of the methods as they progress through these projects. Additionally, students will learn to create quantifiable domain‐specific metrics of interest (cost models) and use techniques to quantitatively assess their results. Students will develop the expertise and an ability to form intuitions which are applicable in other domains.
This course will feature guest lectures from domain experts who will demonstrate how innovative analytic techniques have been transformative and, as a result, generated significant societal impact.
Recommended Text
- Class Notes and Lecture Slides
- Trevor Hastie, Robert Tibshirani, and Jerome Friedman, “The Elements of Statistical Learning: Data Mining, Inference, and Prediction”
Further Reading and Sample Problems
- Daphne Koller and Nir Freidman, “Probabilistic Graphical Models: Principles and Techniques”
- Professor Ravi Iyer’s ECE 313 Class Notes link
Course Structure, Objectives and Learning Outcomes
Lectures: You will be introduced to real-world problems of societal importance (e.g., Safety of AVs, Health Analytics, Large-scale Infrastructures) and their solutions (using e.g., Bayesian networks, Factor Graphs, Large Language Models (LLMs))
Mini projects: There will be two mini-projects common for all students and an additional mini project for 4 credit hour students. These projects will provide hands-on experience with applications of data analytics/machine learning. Students work in groups and follow detailed instructions to build end‐to‐end workflows to solve real‐world data science problems.
In-class activities: Students in small groups will work on realistic design and assessment problems including hands-on modeling with support from instructors and TA’s. There will be approximately 6 in-class activities expected to be completed by the group during class. Attendance is mandatory.
Homework assignments: You will be given theoretical questions, and small programming assignments to strengthen your understanding of the methods learned in lectures.
Course Outcomes: At the end of the course, students will have learned:
- to handle complex high-dimensional data;
- how and when to apply ML-based solutions such as Bayesian Models (Hidden Markov Models/Factor Graphs) building up to LLMs (Role of Transformers, neural networks, reinforcement learning (RL) and finetuning); and
- how to derive insights by combining model solutions with domain knowledge.
Prerequisites
Basic probability and basic programming skills are essential. ECE 313 or CS 361 (Statistics and Probability), and exposure to Python.HW0 to test basic probability skills. Talk to the instructor if you find HW0 to be difficult.
Timeline
There are 45 hours lectures (30 hours classroom lectures, quizzes and presentations & 15 hours hands‐on data analytics mini projects), over 15 weeks in the fall semester.
Lecture Electronics Policy
During the lectures, and in class activities, cell phones or similar non‐class use of electronics are NOT allowed. If, due to unforeseen circumstances, the student needs access to her/his cell phone, she/he shall inform the instructor in the beginning of the lecture and should sit in a way (typically furthest from the board) not to allow any students around them to be disturbed.
Attendance Policy
Attendance to all lectures, and in-class/group activities are required (15% of total grade). There will be in‐class assignments and class participation is graded. Students are advised to contact both the TAs and the instructor via a private post on Piazza (before the beginning of the lecture) if they are to miss a lecture due to unforeseen circumstances. Instructor and TAs reserve the right to take class attendance. Class attendance includes data analytics lab hours. Students can miss no more than one group activity. Note that group activities are only tentatively scheduled.
DRES Accomodations
DRES requirements must be reported to instructor/TAs by the end of 1st week.
Evaluation
We will compute the final grade for undergraduates and graduate students based on this allocation:
Table 1. Three Credit Hour Students
Activity | Grade (Percentage) | Details |
---|---|---|
Mini-Projects 1, 2 | 30% | (MP1 12%, MP2 18%) |
Midterm and Final | 30% | |
Class Participation | 15% | |
In-class Activities | 15% | |
Homework | 10% | |
Total | 100% |
Table 2. Four Credit Hour Students
Activity | Grade (Points) | Details |
---|---|---|
Mini-Projects 1, 2 | 30 points | (MP1 12, MP2 18) |
Midterm and Final | 30 points | |
Mini-Projects 3 | 25 points | |
Class Participation | 15 points | |
In-class Activities | 15 points | |
Homework | 10 points | |
Total | 125 points | Prorated to 100% for letter grade assignment |
More on Mini-Projects
- Mini-projects will be announced in class and posted on the class website
- Full credit for submissions on time.
- Late submission policy: 10% will be taken off for every day, prorated (up to 4 days max). 0 credit after that.
- Groups Policy: Students will form groups (3 persons) for the project starting in week 1, otherwise TAs will form the groups for you.
- While we encourage discussions, submitting identical material is not allowed and will incur appropriate penalties.
- We will hold additional office hours/discussion sessions related to the mini-projects in progress. You are strongly encouraged to attend. Location: TBA 4pm-5pm on Fridays. No discussion in the first week.
- Project descriptions and due dates will be posted on the class website under Student Projects.
- There will be a resources section related to projects.
- For additional questions and discussions will be hosted on Campuswire
- Students will follow detailed instructions to build end‐to‐end workflows to solve real‐world data science problems.
Graduate Students/Four Credit Hours Students Project
- Graduate/four credit hours students will either work on an additional mini-project (mini-project 3) assigned by the instructors, or define their own mini-project with defined goals and deliverables in consultation with the instructor/TAs.
Total Hours
- Lectures: 28 * 1.25 hours = 35 hours
- Discussions: 5 * 1 hour = 5 hours (Optional: slides available on class website)
- Midterm exam: 1 * 1 hour = 1 hour
- Final exam: 1 * 3 hours = 3 hours
- Professor Office hours: 14 * 1 hour = 14 hours (additional hours available via appointment)
- TA Office hours: 14 * 1 = 14 hours (additional hours via appointment)