Week Date Lecture Topics Assigned Due (1:00 pm on the given day)
1 Mar 30
Apr 1 		Introduction [slides]
Operationalized Fairness Criteria [slides] [slides-a] 		HW 1 release (Apr 2)
2 Apr 6
Apr 8		 Guest Lecture by Bo Li
No Class 		Exploratory project release (Apr 9)
3 Apr 13
Apr 15		 Guest Lecture by David Engstrom
Calibration & Fairness [slides] [slides-a]
Learning Group Fair Models [slides] [slides-a], Fair Models via Constrained Optimization [slides] [slides-a]
4 Apr 20
Apr 22		 Individual Fairness [slides] [slides-a], Bias in NLP [slides] [slides-a] , Fairness & Causality
Fairness Socio-Technical Analysis [slides]
HW 1 due (Apr 20)
Socio-tech summary due (Apr 24)
5 Apr 27
Apr 29		 Explainability [slides] [slides-a] LIME [slides] [slides-a], Shapley Values & SHAP [slides] [slides-a],
Saliency Maps [slides] [slides-a], , Exemplar-Based Explanations [slides-a] 		HW 2 release (Apr 27) Exploratory project due (Apr 27)
Final project proposal due (May 1)
6 May 4
May 6		 Explainability Socio-Technical Analysis with guest Manuela Travaglianti [slides-a][Ethics Toolkit accessible via form]
Guest Lecture by Chris Potts [slides] 		Socio-tech summary due (May 8)
7 May 11
May 13 		Concept-Based Explanations [slides-a] , Counterfactual Explanations [slides-a]
Differential Privacy [slides-a] 		HW 3 release (May 11) HW 2 due (May 11)
8 May 18
May 20		 Differential Privacy -- continued
Learning with Differential Privacy [slides-a], Federated Learning [slides] 		Final project milestone (May 20)
9 May 25
May 27		 NO CLASS (Memorial Day)
Guest Lectures: Attacks on LLMs & Citations for Trust and Verifiability 		HW 3 due (May 27)
10 June 1
June 3		 Large Language Models and the Ethics of AI [slides-a]
Closing Discussion on Trust in AI
Poster session on June 2, 2:00 pm - 4:00 pm at AT&T Patio, Gates
Project final report due June 8, 1:00 pm (no late days)