Search Results for author: Harini Suresh

Found 16 papers, 5 papers with code

Participation in the age of foundation models

no code implementations29 May 2024 Harini Suresh, Emily Tseng, Meg Young, Mary L. Gray, Emma Pierson, Karen Levy

In addition to the "foundation" layer, our framework proposes the "subfloor'' layer, in which stakeholders develop shared technical infrastructure, norms and governance for a grounded domain, and the "surface'' layer, in which affected communities shape the use of a foundation model for a specific downstream task.

Improved Text Classification via Test-Time Augmentation

no code implementations27 Jun 2022 Helen Lu, Divya Shanmugam, Harini Suresh, John Guttag

Test-time augmentation -- the aggregation of predictions across transformed examples of test inputs -- is an established technique to improve the performance of image classification models.

Binary Classification Image Classification +2

Saliency Cards: A Framework to Characterize and Compare Saliency Methods

1 code implementation7 Jun 2022 Angie Boggust, Harini Suresh, Hendrik Strobelt, John V. Guttag, Arvind Satyanarayan

Moreover, with saliency cards, we are able to analyze the research landscape in a more structured fashion to identify opportunities for new methods and evaluation metrics for unmet user needs.

Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs

no code implementations24 Jan 2021 Harini Suresh, Steven R. Gomez, Kevin K. Nam, Arvind Satyanarayan

To ensure accountability and mitigate harm, it is critical that diverse stakeholders can interrogate black-box automated systems and find information that is understandable, relevant, and useful to them.

Descriptive Interpretable Machine Learning

Misplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Making

1 code implementation22 May 2020 Harini Suresh, Natalie Lao, Ilaria Liccardi

ML decision-aid systems are increasingly common on the web, but their successful integration relies on people trusting them appropriately: they should use the system to fill in gaps in their ability, but recognize signals that the system might be incorrect.

BIG-bench Machine Learning Decision Making +1

A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle

no code implementations28 Jan 2019 Harini Suresh, John V. Guttag

As machine learning (ML) increasingly affects people and society, awareness of its potential unwanted consequences has also grown.

BIG-bench Machine Learning

Racial Disparities and Mistrust in End-of-Life Care

1 code implementation11 Aug 2018 Willie Boag, Harini Suresh, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

There are established racial disparities in healthcare, including during end-of-life care, when poor communication and trust can lead to suboptimal outcomes for patients and their families.

Applications

Modeling Mistrust in End-of-Life Care

1 code implementation30 Jun 2018 Willie Boag, Harini Suresh, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

In this work, we characterize the doctor-patient relationship using a machine learning-derived trust score.

BIG-bench Machine Learning Sentiment Analysis

Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU

1 code implementation7 Jun 2018 Harini Suresh, Jen J. Gong, John Guttag

In this work, we present a two-step framework to 1) learn relevant patient subgroups, and 2) predict an outcome for separate patient populations in a multi-task framework, where each population is a separate task.

Clinical Intervention Prediction and Understanding using Deep Networks

no code implementations23 May 2017 Harini Suresh, Nathan Hunt, Alistair Johnson, Leo Anthony Celi, Peter Szolovits, Marzyeh Ghassemi

Real-time prediction of clinical interventions remains a challenge within intensive care units (ICUs).

The Use of Autoencoders for Discovering Patient Phenotypes

no code implementations20 Mar 2017 Harini Suresh, Peter Szolovits, Marzyeh Ghassemi

We use autoencoders to create low-dimensional embeddings of underlying patient phenotypes that we hypothesize are a governing factor in determining how different patients will react to different interventions.

Feature Representation for ICU Mortality

no code implementations16 Dec 2015 Harini Suresh

Results indicate that the introduced "hill" representation outperforms both the binary and linear representations, the hill representation thus has the potential to improve existing models of ICU mortality.

ICU Mortality L2 Regularization

Autodetection and Classification of Hidden Cultural City Districts from Yelp Reviews

no code implementations12 Jan 2015 Harini Suresh, Nicholas Locascio

Topic models are a way to discover underlying themes in an otherwise unstructured collection of documents.

Clustering General Classification +1

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