23-Aug |
Slides,
Recording |
Course Intro and Logistics |
Ravi Iyer |
Presentation signup (via Piazza) |
|
Reliability, Fairness and Ethics |
25-Aug |
Slides,
Recording |
Reliability, Security and Safety in Real-world Systems |
Ravi Iyer |
|
Readings
Vision Paper: Grand Challenges in Resilience: Autonomous System Resilience through Design and Runtime Measures Basic concepts and taxonomy of dependable and secure computing |
30-Aug |
Slides,
Recording |
Trustworthy AI and Fairness |
Ravi Iyer |
|
Readings
Fair ML (Classification)
On the Applicability of ML Fairness Notions
The impact of site-specific digital histology signatures on deep learning model accuracy and bias
|
01-Sep |
Slides,
Recording |
Fairness/Bias Assessment |
Student Presenter |
Project signup (via Piazza) |
Paper 1: The Landscape and Gaps in Open Source Fairness Toolkits Paper 2: The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning
Optional Readings: Improving fairness in machine learning systems: What do industry practitioners need?
How to Better Understand Trade-offs Involving Group Fairness |
06-Sep |
LABOR DAY HOLIDAY |
08-Sep |
Slides,
Recording |
Game-theory and Reliability |
Student presenter |
|
Paper 1: Game-Theoretic Methods for Robustness, Security, and Resilience of CPS Control Systems Paper 2: Hierarchical Game-Theoretic Planning for Autonomous Vehicles |
Robustness |
13-Sep |
Slides,
Recording |
Uncertainty |
Ravi Iyer + Student presenter |
|
Paper: Evaluating Uncertainty Quantification in End-to-End Autonomous Driving
Control
Background Readings:
"Uncertainty in deep learning" Introduction: The Importance of Knowing What We Don’t Know
Bayesian Deep Learning
Learning Dynamic Bayesian Networks
Optional Readings:
On Calibration of Modern Neural Networks
On Pitfalls in OoD Detection: Predictive Entropy Considered Harmful
Exploring uncertainty measures in deep networks
|
15-Sep |
Recording |
Guest Lecture Helping Vehicles Make Safer Choices for Themselves |
General Motors (Jason Ditman, Derek Puszcz) |
HW 1 |
|
20-Sep |
Slides,
Recording |
Generative Adversarial Networks |
Ravi Iyer |
|
Background Reading: Generative adversarial nets (NIPS 2014)
Optional Readings:
DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing
Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data
Generative Adversarial Network for Wireless Signal Spoofing
Testing DNN-based Autonomous Driving Systems under Critical Environmental Conditions |
22-Sep |
Slides,
Recording |
Long-tail learning |
Student presenter |
|
Paper: Learning to model the tail
Optional Readings:
Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions
Long tail challenge (Waymo)
Addressing AI tail cases |
27-Sep |
Slides,
Recording |
Adversarial Robustness |
Student presenter |
|
Paper:Improving Adversarial Robustness via Channel-wise Activation Suppressing |
Verification and Certification |
29-Sep |
Slides,
Recording |
Formal Verification Methods |
Student presenter |
|
Paper: Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World |
04-Oct |
Recording |
Group Discussion: Robustness challenges in real-world AI deployment |
Ravi Iyer + Student presenter |
Details here |
|
06-Oct |
Recording |
Project proposal presentation |
Student presenter |
|
|
11-Oct |
Recording |
Guest Lecture: Detection is not Enough - Low-Cost Error and Attack Recovery in Autonomous Systems |
Prof. Karthik Pattabiraman |
HW 2 |
|
13-Oct |
Slides,
Recording |
Fault-Injection |
Student presenter |
|
Paper ML-based Fault Injection for Autonomous Vehicles |
18-Oct |
Recording |
Guest Lecture: Bias and Fairness in Healthcare |
Dr. Joseph A. Whittaker |
HW 3 |
|
20-Oct |
Slides,
Recording |
Fuzz Testing |
Student presenter |
|
Paper DeepHunter: A Coverage-Guided Fuzz Testing Framework for Deep Neural Networks |
Security/Privacy |
25-Oct |
Slides,
Recording |
Malware Attacks |
Student presenter |
|
Paper Ml-driven malware that targets av safety |
27-Oct |
Slides,
Recording |
Trojan Attacks and Stealing Models |
Student presenter |
|
|
01-Nov |
|
Group Discussion |
Ravi Iyer and Student presenter |
|
|
Explanability/ Interpretability |
03-Nov |
Slides,
Recording |
Explainable AI |
Student presenter |
|
Paper
On the Connections between Counterfactual Explanations and Adversarial Examples
Optional Readings:
The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
Improving the accuracy of medical diagnosis with causal machine learning
If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques
|
08-Nov |
Recording |
Guest Lecture: Post-hoc Explanations |
Dr. Karthikeyan Shanmugam |
HW 4 |
Background Reading Counterfactual vs Contrastive Explanations in Artificial Intelligence |
10-Nov |
Slides,
Recording |
Interpretability |
Student presenter |
|
Paper: Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) Applications: Concept-based model explanations for Electronic Health Records
Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making
Optional Reading: On the Interpretability of Artificial Intelligence in Radiology: Challenges and Opportunities
|
15-Nov |
Slides,
Recording |
Model Debugging |
Student presenter |
|
Paper Debugging Tests for Model Explanations
Optional Readings On Human Predictions with Explanations and Predictions of
Machine Learning Models: A Case Study on Deception Detection
|
15-Nov |
|
Midterm Project Presentation |
Student presenter |
Project Reports due on 14th Nov, 11:00am CT |
Details here |
New Problems |
17-Nov |
Slides,
Recording |
Causal Systems |
Student Presenter |
|
Paper: Sage: Practical & Scalable ML-Driven Performance Debugging in Microservices |
22-Nov |
|
FALL BREAK |
|
|
|
24-Nov |
|
FALL BREAK |
|
|
|
29-Nov |
Slides,
Recording |
Reinforcement Learning/ Multi-agent Systems |
|
|
Paper: Measuring the Reliability of Reinforcement Learning Algorithms
Optional Reading
RLiable: Towards Reliable Evaluation & Reporting in Reinforcement Learning
|
01-Dec |
Slides,
Recording |
Summarization and Evolving Themes |
Ravi Iyer |
|
|
06-Dec |
|
Course Review and Interesting Paper |
Student presenter |
|
|
08-Dec |
|
Path Forward |
Ravi Iyer |
|
|
10-Dec |
|
Final Project Presentation |
Student Presenter |
|
|