Evaluating resilience of deep learning models

 

Guardado en:
Detalles Bibliográficos
Autores: Rojas, Elvis, Nicolae, Bogdan, Meneses, Esteban
Formato: artículo
Fecha de Publicación:2020
Descripción:Deep learning applications have become a valuable tool to solve complex problems in many critical areas. It is important to provide reliability on the outputs of those applications, even if failures occur during execution. In this paper, we present a reliability evaluation of three deep learning models. We use an ImageNet dataset and a homebrew fault injector to make all the tests. The results show there is a difference in failure sensitivity among the models. Also, there are models that despite an increase in the failure rate can keep the resulting error values low.
País:Repositorio UNA
Institución:Universidad Nacional de Costa Rica
Repositorio:Repositorio UNA
Lenguaje:Inglés
OAI Identifier:oai:null:11056/26727
Acceso en línea:http://hdl.handle.net/11056/26727
https://doi.org/10.18845/tm.v33i5.5071
Palabra clave:MODELOS
APRENDIZAJE PROFUNDO (APRENDIZAJE AUTOMÁTICO)
RESILIENCIA
SEGURIDAD (INFORMÁTICA)
INYECCIÓN DE FALLOS
TOLERANCIA A FALLOS
MODELS
DEEP LEARNING (MACHINE LEARNING)
RESILIENCE
SECURITY (COMPUTING)
FAULT INJECTION
FAULT TOLERANCE