24-784 Trustworthy AI Autonomy (TAIAT), Spring 2021

Instructor — Prof. Ding Zhao
Teaching assistants — Mansur Arief, Michael Laudenbach
Course linksCanvas site, Course webpage

Course objective — Machine learning is a fast developing field. This is a big opportunity for young generation but also a big challenge as one may get lost in the pyramid of technical news and papers. This course aims to achieve two goals:
  • Help students have a high-level understanding of the fast-developing TAIAT area, quickly grasp key concepts and skills, and get familiar with the latest technological tools in the early phase of their graduate program, so that they could focus on a direction to establish their expertise;
  • Develop full-cycle research capabilities including paper reviews, writing research proposals, milestone reports, academic papers, conference-style paper reviews, making presentations, and serving as an academic critic.

Course structure — The course consists of two modules:
  • Module 1: eight fundamental topics that covers trustworthy AI autonomy from a high level perspective:
    • Latent space visualization
    • Adversarial machine learning
    • Generative models
    • Rare-event learning
    • Sequential decisions making - model-free methods
    • Sequential decisions making - model-based methods
    • Stochastic functional approximation
  • Module 2: five hot topics in the field:
    • Adversarial AI
    • Safe AI
    • AI Evaluation
    • Hierarchical AI
    • Applied AI to real-world autonomy

Textbook — No textbook. Lecture slides will be available on Canvas. Reading materials are listed on the course schedule.

Tentative lecture schedule for Spring 2021 — Below lists the tentative outline. It will be modified depending upon our progress throughout the semester.

Week Day, Date Lec# Topic
1 Tuesday, Feb 2, 2021 1 Overview [Slide]
1 Thusrday, Feb 4, 2021 2 Latent space visualization: basics of deep learning, deconvnet [Slide 1, Slide 2]
2 Tuesday, Feb 9, 2021 3 Adversarial machine learning: poisoning, evasion, FGSM, robust physical attack, randomization, robust AI [Slide]
2 Thursday, Feb 11, 2021 4 Probabilistic evaluation of AI autonomy: imbalanced datasets issue, importance sampling, accelerated evaluation, IQ test of AI [Slide]
3 Tuesday, Feb 16, 2021 5 Generative model: VAE, GAN, and normalizing flow [Slide]
3 Thursday, Feb 18, 2021 6 Sequential decision making under uncertainty - model free methods: reinforcement learning, value-based RL, policy-based RL, value-policy-based RL [Slide]
4 Tuesday, Feb 23, 2021 No class
4 Thursday, Feb 25, 2021 7 Sequential decision making under uncertainty - model based methods: CEM, LQR, MPC[Slide]
5 Tuesday, Mar 2, 2021 8 Sequential decision making under uncertainty - model based methods: model-based RL, safe RL [Slide]
5 Thursday, Mar 4, 2021 9 Stochastic functional approximation: Gaussian processes[Slide]
6 Tuesday, Mar 9, 2021 10 Stochastic functional approximation: GP-based reinforcement learning [Slide]
6 Thursday, Mar 11, 2021 11 Meetings with Prof Zhao to discuss your research proposal
7 Tuesday, Mar 16, 2021 12 Adversarial AI
7 Thursday, Mar 18, 2021 13 Adversarial AI
8 Tuesday, Mar 23, 2021 14 Guest lecture: Prof. Bo Li (UIUC) [Slide]
8 Thursday, Mar 25, 2021 15 Trustworthy reinforcement learning [Slide]
9 Tuesday, Mar 30, 2021 16 Safe AI
9 Thursday, Apr 1, 2021 17 Safe AI
10 Tuesday, Apr 6, 2021 18 AI Evaluation
10 Thursday, Apr 8, 2021 19 AI Evaluation
11 Tuesday, Apr 13, 2021 20 Hierarchical AI structures, trees, and neural processes [Slide]
11 Thursday, Apr 15, 2021 No class
12 Tuesday, Apr 20, 2021 21 Hierarchical AI
12 Thursday, Apr 22, 2021 22 Hierarchical AI
13 Tuesday, Apr 27, 2021 23 Applied AI for real-world problems
13 Thursday, Apr 29, 2021 24 Applied AI for real-world problems
14 Tuesday, May 4, 2021 25 Meetings with Prof Zhao to discuss your final project and future career
14 Thursday, May 6, 2021 26 Final presentation
14 Friday, May y, 2021 27 Poster expo

Accommodations — If you have a disability and have an accommodations letter from the Disability Resources office, I encourage you to discuss your accommodations and needs with me as early in the semester as possible. I will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, I encourage you to contact them at access@andrew.cmu.edu.

Academic Integrity Policy — Honesty and transparency are important features of a good scholarship. On the flip side, plagiarism and cheating are serious academic offenses with serious consequences. If you are discovered engaging in either behavior in this course, you will earn a failing grade on the assignment in question, and further disciplinary action may be taken. For a clear description of what counts as plagiarism, cheating, and/or the use of unauthorized sources, please see the University‚Äôs Policy on Academic Integrity.

Take Care of Yourself — Take care of yourself. Do your best to maintain a healthy lifestyle this semester by eating well, exercising, avoiding drugs and alcohol, getting enough sleep, and taking some time to relax. This will help you achieve your goals and cope with stress. All of us benefit from support during times of struggle. There are many helpful resources available on campus and an important part of the college experience is learning how to ask for help. Asking for support sooner rather than later is almost always helpful. If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support. Counseling and Psychological Services (CaPS) is here to help: call 412-268-2922 and visit their website at http://www.cmu.edu/counseling/. Consider reaching out to a friend, faculty, or family member you trust for help getting connected to the support that can help.