Administrivia

Prerequisites

Basic probability (ECE 313 or equivalent), machine learning (ECE 498DS or CS 446 or equivalent) and basic programming skills (such as Python or R or Matlab) are essential.

Evaluation

We will compute the final grade using the following table:

Activity Grade Details
Paper Presentation and Reviews 30% Presenter + Respondent + Reviews
Class Participation 20% Group Discussion + Attendance + Paper Critique
Guest Lecture Critique 10% Review and critique the guest lectures
Course Project 40% Proposal(5%) + Mid-term Report(10%) + Final Presentation and Report(25%)

Credit Policy

  • Student attendance in all lectures is required. Class participation, which includes in-class activities and group discussions, will be evaluated.
  • Late submission policy: No late submissions allowed.
  • While we encourage discussions, submitting identical material is not allowed and will incur appropriate penalties.

Paper Presentation & Reviews

During each presentation session, one student presenter will present and summarize the key findings focusing on the strengths. Another student (respondent) will lead the post-presentation discussion and will be responsible for critiquing the paper. Students need to sign-up for presenter slots while the instructors will assign the respondents.
Students who are not presenting in that session are expected to write short reviews on Campuswire for the papers being presented. We strongly encourage you to engage in a discussion with your classmates instead of summarizing the paper.

For Reviewers
  • Description: 2 pages max. 1 paragraph on the core idea of the paper, followed by list of pros and cons of the approach, and any questions/criticisms/thoughts about the paper.
  • Grading Criteria: Argumentative critique (Pros/Cons), Creative comments about addressing issues or improving the paper.
  • Due: Night before the day of presentation at 10pm
For Presenters
  • Sign-up: By 31 Aug (Thursday) (Sign-up sheet link to be updated)
  • Description: 10-12 slides max (20 min for paper, 5 min critique, 5 min for questions). 2-3 slides on motivation and background. 3-5 slides on core ideas of the paper. 2-3 slides on experimental data. 3-5 slides on your thoughts/analysis/questions/discussion points about the paper. Include slides summarizing Campuswire discussion about paper.
  • Due: 9 am on the day of the presentation (Upload on Canvas)
For Respondents
  • Description: Lead the discussion with 3-4 key points analyzing and critiquing the paper. Summarize the paper discussion at the end of the lecture (5 min critique, 5 min for questions/summary).

Course Project

The final project is an open-ended research project that can target the design, development of dependable AI/ML systems and will deepen the class's understanding. This can include evaluation of AI/ML systems using analytical models or measurements, novel application of existing techniques in reliable and trustworthy AI to different scenarios or analysis of vulnerabilities using simulators and fault-injection methods. We will also provide a list of project topics for reference, but you are free to come up with your own ideas.

Project Team Signup

Students will form groups of two for the final project early in week 4. One member of each project team should signup the team on Campuswire by TBD. We will also initiate a Campuswire post to help you in team search. Failure to form project group by the deadline will lead to TA assigning the student to a group.

Project Requirements
  1. Initial project proposal presentation (due starting of Oct, date to be announced)
  2. Mid-term Report: A short presentation to report on your initial progress including a critique of the literature.
  3. Final Presentation: Encompassing initial goals, results achieved, method/approach, major accomplishments.
  4. Final report
Project Ideas

Some of the project topics from last year:

  • Modelling fault-tolerant behavior of brain during neuronal injury in Alzheimer’s disease
  • Network Traffic Management using Fair Decision-Making
  • Program Assertions for Deep Neural Networks
  • Fault-injection and performance assessment of UAVs
  • Leveraging importance sampling for rare event simulation in autonomous driving
You can find some interesting topics on recent conference workshops focusing on Safe and Trustworthy AI:
Conferences for Project Ideas

  • International Conference on Dependable Systems and Networks (DSN)
  • Neural Information Processing Systems (NeurIPS)
  • International Conference on Machine Learning (ICML)
  • International Conference on Computer Aided Verification (CAV)
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Usenix Security
  • IEEE Symposium on Security and Privacy