Cargando…
One-shot generalization in humans revealed through a drawing task
Humans have the amazing ability to learn new visual concepts from just a single exemplar. How we achieve this remains mysterious. State-of-the-art theories suggest observers rely on internal ‘generative models’, which not only describe observed objects, but can also synthesize novel variations. Howe...
Autores principales: | Tiedemann, Henning, Morgenstern, Yaniv, Schmidt, Filipp, Fleming, Roland W |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
eLife Sciences Publications, Ltd
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9090327/ https://www.ncbi.nlm.nih.gov/pubmed/35536739 http://dx.doi.org/10.7554/eLife.75485 |
Ejemplares similares
-
A dataset for evaluating one-shot categorization of novel object classes
por: Morgenstern, Yaniv, et al.
Publicado: (2020) -
An image-computable model of human visual shape similarity
por: Morgenstern, Yaniv, et al.
Publicado: (2021) -
Superordinate Categorization Based on the Perceptual Organization of Parts
por: Tiedemann, Henning, et al.
Publicado: (2022) -
The role of semantics in the perceptual organization of shape
por: Schmidt, Filipp, et al.
Publicado: (2020) -
A Developmental Perspective in Learning the Mirror-Drawing Task
por: Julius, Mona Sharon, et al.
Publicado: (2016)