Výsledky vyhledávání - "Hurtado, Carlos A."

Report

Out-of-Distribution Detection through Soft Clustering with Non-Negative Kernel Regression

Autor: Gulati, Aryan, Dong, Xingjian, Hurtado, Carlos, Shekkizhar, Sarath, Swayamdipta, Swabha, Ortega, Antonio

As language models become more general purpose, increased attention needs to be paid to detecting out-of-distribution (OOD) instances, i.e., those not belonging to any of the distributions seen during training. Existing methods for detecting OOD data

Externí odkaz: http://arxiv.org/abs/2407.13141

Zobrazit plný text záznamu

Report

Seeding with Differentially Private Network Information

Autor: Rahimian, M. Amin, Yu, Fang-Yi, Liu, Yuxin, Hurtado, Carlos

In public health interventions such as the distribution of preexposure prophylaxis (PrEP) for HIV prevention, decision makers rely on seeding algorithms to identify key individuals who can amplify the impact of their interventions. In such cases, bui

Externí odkaz: http://arxiv.org/abs/2305.16590

Zobrazit plný text záznamu

Akademický článek

Schottky Diode Leakage Current Fluctuations: Electrostatically Induced Flexoelectricity in Silicon.

Autor: Hurtado, Carlos¹ (AUTHOR), MacGregor, Melanie² (AUTHOR), Chen, Kai³ (AUTHOR), Ciampi, Simone¹ (AUTHOR) simone.ciampi@curtin.edu.au

Publikováno v: Advanced Science. 10/16/2024, Vol. 11 Issue 38, p1-9. 9p.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs

Autor: Hurtado, Carlos, Shekkizhar, Sarath, Ruiz-Hidalgo, Javier, Ortega, Antonio

Modern machine learning systems are increasingly trained on large amounts of data embedded in high-dimensional spaces. Often this is done without analyzing the structure of the dataset. In this work, we propose a framework to study the geometric stru

Externí odkaz: http://arxiv.org/abs/2210.17475

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání