Cargando…
Communicating artificial neural networks develop efficient color-naming systems
Words categorize the semantic fields they refer to in ways that maximize communication accuracy while minimizing complexity. Focusing on the well-studied color domain, we show that artificial neural networks trained with deep-learning techniques to play a discrimination game develop communication sy...
Autores principales: | Chaabouni, Rahma, Kharitonov, Eugene, Dupoux, Emmanuel, Baroni, Marco |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
National Academy of Sciences
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8000426/ https://www.ncbi.nlm.nih.gov/pubmed/33723064 http://dx.doi.org/10.1073/pnas.2016569118 |
Ejemplares similares
-
Self-backpropagation of synaptic modifications elevates the efficiency of spiking and artificial neural networks
por: Zhang, Tielin, et al.
Publicado: (2021) -
Temporal dissociation of neural activity underlying synesthetic and perceptual colors
por: Teichmann, Lina, et al.
Publicado: (2021) -
Recognition of Latin scientific names using artificial neural networks
por: Little, Damon P.
Publicado: (2020) -
Universals of word order reflect optimization of grammars for efficient communication
por: Hahn, Michael, et al.
Publicado: (2020) -
Naming guides how 12-month-old infants encode and remember objects
por: LaTourrette, Alexander S., et al.
Publicado: (2020)