Cargando…
SpatialSim: Recognizing Spatial Configurations of Objects With Graph Neural Networks
An embodied, autonomous agent able to set its own goals has to possess geometrical reasoning abilities for judging whether its goals have been achieved, namely it should be able to identify and discriminate classes of configurations of objects, irrespective of its point of view on the scene. However...
Autores principales: | Teodorescu, Laetitia, Hofmann, Katja, Oudeyer, Pierre-Yves |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8826049/ https://www.ncbi.nlm.nih.gov/pubmed/35156011 http://dx.doi.org/10.3389/frai.2021.782081 |
Ejemplares similares
-
Configural relations in humans and deep convolutional neural networks
por: Baker, Nicholas, et al.
Publicado: (2023) -
Graph Neural Networks for Maximum Constraint Satisfaction
por: Tönshoff, Jan, et al.
Publicado: (2021) -
Graph neural networks for preference social recommendation
por: Ma, Gang-Feng, et al.
Publicado: (2023) -
Convolutional neural network-based ensemble methods to recognize Bangla handwritten character
por: Shibly, Mir Moynuddin Ahmed, et al.
Publicado: (2021) -
Generalizable Machine Learning in Neuroscience Using Graph Neural Networks
por: Wang, Paul Y., et al.
Publicado: (2021)