Detailed Syllabus


Week Date Lecture Topics Location Assigned Due
1 Apr 3
Apr 5 		Introduction [slides]
Operationalized Fairness Criteria [slides, slides-a] 		200-305 HW 1 released (Apr 6)
2 Apr 10
Apr 12		 Calibration & Fairness [slides, slides-a], Learning Group "Fair" Models [slides, slides-a]
Guest Lecture by David Engstrom -- "The Legal Perspective" 		200-305
3 Apr 17
Apr 19		 Fair Models via Constrained Optimization [slides, slides-a], Individual Fairness [slides, slides-a]
Bias in NLP [slides, slides-a], Fairness and Causality [slides, slides-a] 		200-305
HW 1(Apr 17)
4 Apr 24
Apr 26		 Fairness Socio-Technical Analysis
Explainability and Transparency [slides, slides-a] Feature Attribution and LIME [slides, slides-a]
200-305 		HW 2 released (Apr 24)
exploratory project released (Apr 27)
socio-tech summary (Apr 26)
5 May 1
May 3		 Shapley Values & SHAP [slides, slides-a], Saliency Maps [slides<, slides-a]
Exemplar-Based Explanations [slides, slides-a], Concept-Based Explanations [slides, slides-a], 		200-305
6 May 8
May 10		 Explainability Socio-Technical Analysis
Counterfactual Explanations [slides, slides-a], Privacy and ML, Differential Privacy [slides, slides-a] 		200-305 final project proposal (May 12)
HW 2 (May 10)
7 May 15
May 17 		Guest Lecture by Rob Reich -- "What Is Fairness?" [slides]
Differential Privacy -- continued 		200-305
HW 3 released (May 17) exploratory project (May 15) socio-tech summary (May 17)
8 May 22
May 24		 Learning with Differential privacy [slides, slides-a] Federated Learning [slides, slides-a]
Large Language Models and the Ethics of AI: Impact, Gaps and Opportunities 		200-305 final project milestone (May 24)
9 May 29
May 31		 Memorial Day -- No class
Guest Lecture by Been Kim on "Beyond AI safety: developing machines that work for us" [slides]
Zoom 		HW 3 (May 31)
10 June 5
June 7		 Privacy Socio-Technical Analysis
Closing Discussion -- Trust in AI [slides] 		200-305 Socio-tech summary (June 7)
poster session CANCELED
project final report due June 12