Cargando…

Integrating Non-monotonic Logical Reasoning and Inductive Learning With Deep Learning for Explainable Visual Question Answering

State of the art algorithms for many pattern recognition problems rely on data-driven deep network models. Training these models requires a large labeled dataset and considerable computational resources. Also, it is difficult to understand the working of these learned models, limiting their use in s...

Descripción completa

Detalles Bibliográficos
Autores principales: Riley, Heather, Sridharan, Mohan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7805953/
https://www.ncbi.nlm.nih.gov/pubmed/33501140
http://dx.doi.org/10.3389/frobt.2019.00125

Ejemplares similares