Data-driven emergence of convolutional structure in neural networks

Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks can discover appropriate representations capable of harnessing the underlying symmetries of their inputs is thus crucial in machine learning and neurosci...

Celý popis

Podrobná bibliografia

Vydané v:	Proceedings of the National Academy of Sciences - PNAS Ročník 119; číslo 40; s. e2201854119
Hlavní autori:	Ingrosso, Alessandro, Goldt, Sebastian
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	United States 04.10.2022
Predmet:	Machine Learning Neural Networks, Computer Neurosciences convolution receptive fields invariance neural networks
ISSN:	1091-6490, 1091-6490
On-line prístup:	Zistit podrobnosti o prístupe
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!