Schedule

This course will proceed in three main parts: overview, deep dives, and conclusion.

Structure

Overview

In the first part of the course we will review ML basics, set norms for interaction and complete a survey of the topics that we will cover for the rest of the semester.

In this part of the class, Professor Brown will lead synchronous sessions. Students will be responsible for reading overviews, refreshing background material, and choosing an area for their course project. Students will start with an introductory demo or replication as a mini project.

Deep Dives

During the middle of the course we will spend one week on each topic. There will be 1-3 papers to read each week.

Students will be responsible for presenting papers in class on a rotating basis.

During this time students will have milestones where they need to complete interim steps for their course project. The first milestone will be a proposal that includes the specific products for the remainder of the milestones based on a template.

Conclusion

We will wrap up by discussing students’ projects in class time, giving substantive feedback prior to the final submissions.

Final projects will be evaluated through a presentation and paper.

Weekly topics

The readings are subject to revision in class up until a presenter is assigned. Topics may also be updated after the first few classes based on student interests and recent publications.

Warning

The first two weeks will be as follows, other papers will liklely be adjusted based on student project topcss

Table 1 Schedule

Date	Topic	Reading	Class
2024-01-23	Introduction	None	introductions, expectation setting
2024-01-25	Probability Review	Model Based ML book: intro & chapter 1 and start of fairml book ch 2.	reading discussion, setting up
2024-01-30	Setting the Stage	The Scientific Method in the Science of Machine Learning, Value-laden Disciplinary Shifts in Machine Learning and Integrating Explanation and Prediction in Computational Social Sciences	Paper Presentation by Dr. Brown
2024-02-01	Meta issues	Roles for computing in social change	Paper Presentation by Dr. Brown
2024-02-06	Missing Data: Intro strategies	Handling Missing Values when Applying Classification Models & Missing data imputation using statistical and machine learning methods in a real breast cancer problem	Paper discussions led by Ryan and Bori
2024-02-08	Missing data with graphical models and causal reasoning	Graphical Models for Inference with Missing Data	Paper discussion led by Reid + performance metric review
2024-02-15	Fairness	Fairml classification chapter (including impossibility proofs) and Emprical comparison paper	Paper discussion by Arlen and Yusra
2024-02-20	Fairness and Causality	FairML Causality chapter and classic bias examples (Machine Bias and Gender Shades and Obermeyer)	Paper discussion by Liam and David
2024-02-22	Bias and STS	Ruha Benjamin	Talk at Welcome center
2024-02-27	Complexity of bias and fairness	and the possibility of fairness	Paper discussion Puja and Victoria
2024-02-29	Latent Variable models	classic: Indian Buffet Process and deep learning:Auto-Encoding Variational Bayes	Paper presentation by Kushas and Niraj
2024-03-05	Interpretable & Explanation Intro	On the Independence of Association Bias and Empirical Fairness in Language Models and [Towards A Rigorous Science of Interpretable Machine Learning] (https://arxiv.org/abs/1702.08608)	Paper presentation by Puja and Liam
2024-03-07	What does Interpretable mean	A Survey of Methods for Explaining Black Box Models Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) and Towards falsifiable interpretability research	Paper presentation by Sarah, Reid, and Borano
2024-03-12	spring break	none	none
2024-03-14	spring break	none	none
2024-03-19	proposal revisions	none	peer review
2024-03-21	proposal revisions	none	peer review
2024-03-26	A Case for Interpretability over Explanation	Why are we explaining black box models and Learning Certifiably optimal rule lists for categorical data	Paper presentation by TBD
2024-03-28	what to/not do with explanation	Actionable Recourse in Linear Classification and Model Reconstruction from Model Explanations	Paper Presentation by Arlen and Bori
2024-04-02	Trust	Formalizing Trust in Artificial Intelligence: Prerequisites, Causes and Goals of Human Trust in AI and trustworthiness of GPT models	Paper Presentation by Victoria and Ryan
2024-04-04	LLMs and risks	GPT3 and Stochastic Parrots	Paper Presentation by Yusra and Kushas
2024-04-09	Generative Models in social contexts	Are Emergent abilities of LLMs a Mirage and Regulating ChatGPT and other Large GenAI models	Paper Presentation by Liam and David
2024-04-11	Multi objective learning	A critical review of multi-objective optimization in data mining: a position paper	Paper Presentation Niraj
2024-04-16	Noisy labels and bias	Recovering from biased data: Can fairness constraints improve accuracy and Learning with Noisy Labels	Paper Presentation by Puja and Kushas
2024-04-18	art/future or work?	tba	Paper Presentation by Niraj
2024-04-23	3 Project Presentations	projects	Paper Presentation by Yusra, Puja, and Liam; Arlen; Ryan & Victoria
2024-04-25	3 Project Presentations	projects	presentations by David; Borano & Kushas

• • 2024-04-18

  • data augmentation?

  • tba

  • Paper Presentation by