Cargando…
Human-like systematic generalization through a meta-learning neural network
The power of human language and thought arises from systematic compositionality—the algebraic ability to understand and produce novel combinations from known components. Fodor and Pylyshyn(1) famously argued that artificial neural networks lack this capacity and are therefore not viable models of th...
Autores principales: | Lake, Brenden M., Baroni, Marco |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10620072/ https://www.ncbi.nlm.nih.gov/pubmed/37880371 http://dx.doi.org/10.1038/s41586-023-06668-3 |
Ejemplares similares
-
Learning and replication of periodic signals in neural-like networks
por: Reinke, R, et al.
Publicado: (1995) -
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning
por: Smith, Justin S., et al.
Publicado: (2019) -
Communicating artificial neural networks develop efficient color-naming systems
por: Chaabouni, Rahma, et al.
Publicado: (2021) -
Breast Cancer Classification through Meta-Learning Ensemble Technique Using Convolution Neural Networks
por: Ali, Muhammad Danish, et al.
Publicado: (2023) -
General differential Hebbian learning: Capturing temporal relations between events in neural networks and the brain
por: Zappacosta, Stefano, et al.
Publicado: (2018)