Cargando…
Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition
Humans quickly and accurately learn new visual concepts from sparse data, sometimes just a single example. The impressive performance of artificial neural networks which hierarchically pool afferents across scales and positions suggests that the hierarchical organization of the human visual system i...
Autores principales: | Rule, Joshua S., Riesenhuber, Maximilian |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7835122/ https://www.ncbi.nlm.nih.gov/pubmed/33510629 http://dx.doi.org/10.3389/fncom.2020.586671 |
Ejemplares similares
-
Population codes enable learning from few examples by shaping inductive bias
por: Bordelon, Blake, et al.
Publicado: (2022) -
Embodied Object Representation Learning and Recognition
por: Van de Maele, Toon, et al.
Publicado: (2022) -
An Active Inference Approach to Modeling Structure Learning: Concept Learning as an Example Case
por: Smith, Ryan, et al.
Publicado: (2020) -
Learning view invariant recognition with partially occluded objects
por: Tromans, James M., et al.
Publicado: (2012) -
Invariant Recognition of Visual Objects: Some Emerging Computational Principles
por: Bart, Evgeniy, et al.
Publicado: (2012)