Schedule

Date Descriiption Guest Lecturer Readings Notes
4/4 Introduction (slides) and Responsible Data Science 101 Prof. Abel Rodriguez  Supplemental Material  
4/11 Introduction to Fairness, Accountability and Transparency Eriq Augustine lead

Critical Questions for Big Data, dana boyd & Kate Crawford.  Information, Communication & Society, 2012. link (QCR #1)

Big Data, Machine Learning, and the Social Sciences: Fairness, Accountability, and Transparency, Hanna Wallach, Medium, 2014. link (QCR #2)

 
4/18 Privacy (slides) Prof. Abhradeep Guha Thakurta

Differential Privacy Survey, Cynthia Dwork, reading #1  (QCR #3)

Differential Privacy at Apple, Abhishek Bhowmick, Julien Freudiger, Abhradeep Thakurta, Andy Vyrros, reading #2 (no QCR required)

supplemental material: Data confidentiality: A review of
methods for statistical disclosure
limitation and methods for
assessing privacy, Gregory J. Matthews and Ofer Harel, Statistics Surveys, vol 5, 2011.  paper

Initial Project Proposal due by 5PM Monday 4/23
4/25 Fairness (slides) Golnoosh Farnadi

Research Priorities for Robust and Beneficial Artificial Intelligence,
Stuart Russell, Daniel Dewey, Max Tegmark, AAAI 2015.  paper (QCR #4[link updated] 

Equality of Opportunity in Supervised Learning, Moritz Hardt, Eric Price, Nathan Srebro, 2016https://arxiv.org/abs/1610.02413   (QCR #5)

 
5/2 Interpretability (slides) Sarah Tan

Survey of interpretability: The Mythos of Model Interpretability https://arxiv.org/abs/1606.03490
(QCR #6)
"Why Should I Trust You?": Explaining the Predictions of Any Classifier: https://arxiv.org/abs/1602.04938. (skim, no QCR)

Please install for hand-on session:

Lime (follow installation instructions here: https://github.com/marcotcr/lime)
Also git clone the repo as we will be running through one or two of the tutorials in this repo
 
Other packages: numpy, matplotlib, sklearn, skimage, xgboost, pandas
5/9 Causality (slides) Dhanya Sridhar  

S. Morgan and C. Winship. Counterfactuals and Causal Inference. Cambridge University Press, 2nd edition, 2015; ch2

G. Imbens and D. Rubin. Causal Inference in Statistics, Social and Biomedical Sciences: An Introduction. Cambridge University Press, 2015; ch1 (optional)

Link to slides: https://cs.nyu.edu/~shalit/tutorial.html

Midterm Project Proposal due

5/16 Reproducibility (slides) Ivo Jimenez

Donoho, D. et al. (2009), Reproducible research in computational harmonic analysis, Comp. Sci. Eng. 11(1):8–18, doi: 10.1109/MCSE.2009.15

M. Liberman, “Replicability vs. reproducibility — or is it the other way around?,” Oct. 2015, http://languagelog.ldc.upenn.edu/nll/?p=21956

QCR #7

Additional readings: link
5/23 Autonomous Vehicles
Sandra Dreisbach
 

Why Self-Driving Cars Must Be Programmed to Kill, MIT Technology Review, 2015  pdf

Should we  be scared of self-driving cars after the Uberfatality? MIT Technology Review, 2018 pdf

QCR #8

 
5/30 Autonomous Weapons (slides)
Anthony Aguirre
 
Reading #1:

Governing Lethal Autonomous Weapon Systems

Reading #2:Defending the Boundary: Constraints and requirements on the use of autonomous Weapon systems under international humanitarian and human rights law (skim)

QCR #9

 
6/6 Project Presentations     Final Project due by 5PM Monday June 11