Revisiting the fragility of influence functions

JR Epifano, RP Ramachandran, AJ Masino, G Rasool - Neural Networks, 2023 - Elsevier
In the last few years, many works have tried to explain the predictions of deep learning
models. Few methods, however, have been proposed to verify the accuracy or faithfulness of …

EvalAttAI: a holistic approach to evaluating attribution maps in robust and non-robust models

IE Nielsen, RP Ramachandran, N Bouaynaya… - IEEE …, 2023 - ieeexplore.ieee.org
The expansion of explainable artificial intelligence as a field of research has generated
numerous methods of visualizing and understanding the black box of a machine learning …

Deployment of a robust and explainable mortality prediction model: The covid-19 pandemic and beyond

JR Epifano, S Glass, RP Ramachandran… - arXiv preprint arXiv …, 2023 - arxiv.org
This study investigated the performance, explainability, and robustness of deployed artificial
intelligence (AI) models in predicting mortality during the COVID-19 pandemic and beyond …

A comparison of feature selection techniques for first-day mortality prediction in the icu

JR Epifano, A Silvestri, A Yu… - … on Circuits and …, 2023 - ieeexplore.ieee.org
First-day mortality prediction is a critical task in the Intensive Care Unit (ICU), as it can help
clinicians identify which patients are at the highest risk for death and thus may need more …

Better Models for High-Stakes Tasks

J Epifano - 2023 - search.proquest.com
The intersection of machine learning and healthcare has the potential to transform medical
diagnosis, treatment, and research. Machine learning models can analyze vast amounts of …

On the explainability of multiple sclerosis disease progression models

MJC de Sousa - 2021 - search.proquest.com
Esclerose múltipla é a doença neurológica mais predominante em jovens adultos
globalmente. A complexidade e heterogencidade da sua progressão, eo consequente …