Search Results for author: Motahhare Eslami

Found 3 papers, 0 papers with code

Investigating Practices and Opportunities for Cross-functional Collaboration around AI Fairness in Industry Practice

no code implementations10 Jun 2023 Wesley Hanwen Deng, Nur Yildirim, Monica Chang, Motahhare Eslami, Ken Holstein, Michael Madaio

In this research, we sought to better understand practitioners' current practices and tactics to enact cross-functional collaboration for AI fairness, in order to identify opportunities to support more effective collaboration.

Fairness

Understanding Practices, Challenges, and Opportunities for User-Engaged Algorithm Auditing in Industry Practice

no code implementations7 Oct 2022 Wesley Hanwen Deng, Bill Boyuan Guo, Alicia DeVrio, Hong Shen, Motahhare Eslami, Kenneth Holstein

Recent years have seen growing interest among both researchers and practitioners in user-engaged approaches to algorithm auditing, which directly engage users in detecting problematic behaviors in algorithmic systems.

Explaining the Black-box Smoothly- A Counterfactual Approach

no code implementations11 Jan 2021 Sumedha Singla, Motahhare Eslami, Brian Pollack, Stephen Wallace, Kayhan Batmanghelich

We adopted a Generative Adversarial Network (GAN) to generate a progressive set of perturbations to a query image, such that the classification decision changes from its original class to its negation.

counterfactual Counterfactual Explanation +5

Cannot find the paper you are looking for? You can Submit a new open access paper.