RNNCon: Contribution Coverage Testing for Stacked Recurrent Neural Networks

Recurrent Neural Networks (RNNs) are applied in safety-critical fields such as autonomous driving, aircraft collision detection, and smart credit. They are highly susceptible to input perturbations, but little research on RNN-oriented testing techniques has been conducted, leaving a threat to a larg...

Descripción completa

Detalles Bibliográficos
Autores principales: Du, Xiaoli, Zeng, Hongwei, Chen, Shengbo, Lei, Zhou
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10048185/
https://www.ncbi.nlm.nih.gov/pubmed/36981408
http://dx.doi.org/10.3390/e25030520

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10048185/
https://www.ncbi.nlm.nih.gov/pubmed/36981408
http://dx.doi.org/10.3390/e25030520

Ejemplares similares