A critique of pure learning and what artificial neural networks can learn from animal brains
Recent gains in artificial neural networks rely heavily on large amounts of training data. Here, the author suggests that for AI to learn from animal brains, it is important to consider that animal behaviour results from brain connectivity specified in the genome through evolution, and not due to un...
Guardado en:
Autor principal: | Anthony M. Zador |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2019
|
Materias: | |
Acceso en línea: | https://doaj.org/article/756ea53345a445f7abb929c988568b60 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
Brain-inspired replay for continual learning with artificial neural networks
por: Gido M. van de Ven, et al.
Publicado: (2020) -
What connectomics can learn from genomics.
por: Patrick B Chen, et al.
Publicado: (2021) -
What can optical engineers learn from Leonardo?
por: Livshits I.L., et al.
Publicado: (2021) -
Neural networks can learn to utilize correlated auxiliary noise
por: Aida Ahmadzadegan, et al.
Publicado: (2021) -
What Can We Learn from Exam Grade Distributions?
por: Daniel Lewin
Publicado: (2021)