Výsledky vyhledávání - "Jacob R. Epifano"

Akademický článek

Efficient Scaling of Bayesian Neural Networks

Autor: Jacob R. Epifano, Timothy Duong, Ravi P. Ramachandran, Ghulam Rasool

Publikováno v: IEEE Access, Vol 12, Pp 150953-150961 (2024)

While Bayesian neural networks (BNNs) have gained popularity for their theoretical guarantees and robustness, they have yet to see a convincing implementation at scale. This study investigates a variational inference-based neural architecture called

Externí odkaz: https://doaj.org/article/bbb458a5c00647f3a06e108ae5019383

Zobrazit plný text záznamu

Revisiting the fragility of influence functions

Autor: Jacob R. Epifano, Ravi P. Ramachandran, Aaron J. Masino, Ghulam Rasool

Publikováno v: Neural Networks. 162:581-588

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 these explanations. Recently, influence functions, which is a method t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::add342c8d112994361be3502e9bfcbf2
https://doi.org/10.1016/j.neunet.2023.03.029

Zobrazit plný text záznamu

Machine Learning Analysis of Digital Clock Drawing Test Performance for Differential Classification of Mild Cognitive Impairment Subtypes Versus Alzheimer’s Disease

Autor: Muhammad Umer, Jacob R. Epifano, Nicholas Calzaretto, Victor Wasserman, Robi Polikar, Sean McGuire, David J. Libon, Russell Binaco, Sheina Emrani

Publikováno v: Journal of the International Neuropsychological Society. 26:690-700

Objective:To determine how well machine learning algorithms can classify mild cognitive impairment (MCI) subtypes and Alzheimer’s disease (AD) using features obtained from the digital Clock Drawing Test (dCDT).Methods:dCDT protocols were administer

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a223b7733dd6014dd544d64029862235
https://doi.org/10.1017/s1355617720000144

Zobrazit plný text záznamu

Towards an Explainable Mortality Prediction Model

Autor: Sharad Patel, Ghulam Rasool, Ravi P. Ramachandran, Jacob R. Epifano

Publikováno v: MLSP

Influence functions are analytical tools from robust statistics that can help interpret the decisions of black-box machine learning models. Influence functions can be used to attribute changes in the loss function due to small perturbations in the in

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6e4cf5e6c5c46eae80c04c65d30f1531
https://doi.org/10.1109/mlsp49062.2020.9231833

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání