This is a tentative schedule.

(Wed, 1/14) Lecture 1: Course Overview

(Wed, 1/21) Lecture 2: Review of ML Models

(Mon, 1/26) Lecture 5: Adversarial Robustness

(Wed, 1/28) Lecture 6: Robust Training

(Mon, 2/2) Lecture 7: Formal Methods for Robustness Verification

(Wed, 2/4) Lecture 8: Jailbreaking LLMs

(Mon, 2/9) Lecture 9: Covariate Shift

(Wed, 2/11) Lecture 10: Label Shift

(Mon, 2/16) Lecture 11: Calibrated Prediction

(Wed, 2/18) Lecture 12: Conformal Prediction

(Mon, 2/23) Lecture 13: Aleatoric vs. Epistemic Uncertainty

(Wed, 2/25) Lecture 14: Uncertainty Quantification for LLMs

(Mon, 3/2) Lecture 15: Review

(Wed, 3/4) Lecture 16: Midterm 1

(Mon, 3/16) Lecture 17: Explainability

(Wed, 3/18) Lecture 18: LIME and SHAP

(Mon, 3/23) Lecture 19: Counterfactual and Concept-Based Explanations

(Wed, 3/25) Lecture 20: Data Attribution Methods

(Mon, 4/30) Lecture 21: Neurosymbolic Learning

(Wed, 4/1) Lecture 22: Background on Reinforcement Learning

(Mon, 4/6) Lecture 23: Reinforcement Learning from Human Feedback

(Wed, 4/8) Lecture 24: Direct Policy Optimization

(Mon, 4/13) Lecture 25: Review

(Wed, 4/15) Lecture 26: Midterm 2

(Mon, 4/20) Lecture 27: Project Presentations

(Wed, 4/22) Lecture 28: Project Presentations

(Mon, 4/27) Lecture 27: Project Presentations

(Wed, 4/29) Lecture 28: Project Presentations