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...
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
-
Editorial: Robots that Learn and Reason: Towards Learning Logic Rules from Noisy Data
por: Moreno, Plinio, et al.
Publicado: (2021) -
Human-Guided Learning for Probabilistic Logic Models
por: Odom, Phillip, et al.
Publicado: (2018) -
A Neural Network With Logical Reasoning Based on Auxiliary Inputs
por: Wan, Fang, et al.
Publicado: (2018) -
Symbolic Learning and Reasoning With Noisy Data for Probabilistic Anchoring
por: Zuidberg Dos Martires, Pedro, et al.
Publicado: (2020) -
Few-Shot Induction of Generalized Logical Concepts via Human Guidance
por: Das, Mayukh, et al.
Publicado: (2020)