Cargando…
Nonlinear reconfiguration of network edges, topology and information content during an artificial learning task
Here, we combine network neuroscience and machine learning to reveal connections between the brain’s network structure and the emerging network structure of an artificial neural network. Specifically, we train a shallow, feedforward neural network to classify hand-written digits and then used a comb...
Autores principales: | Shine, James M., Li, Mike, Koyejo, Oluwasanmi, Fulcher, Ben, Lizier, Joseph T. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Springer Berlin Heidelberg
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8639979/ https://www.ncbi.nlm.nih.gov/pubmed/34859330 http://dx.doi.org/10.1186/s40708-021-00147-z |
Ejemplares similares
-
Generalised Measures of Multivariate Information Content
por: Finn, Conor, et al.
Publicado: (2020) -
Topological invariant and anomalous edge modes of strongly nonlinear systems
por: Zhou, Di, et al.
Publicado: (2022) -
Thermal control of the topological edge flow in nonlinear photonic lattices
por: Jung, Pawel S., et al.
Publicado: (2022) -
Topologically reconfigurable magnetic polaritons
por: Li, Min, et al.
Publicado: (2022) -
Dynamic Reconfiguration of Functional Topology in Human Brain Networks: From Resting to Task States
por: Zhang, Wenhai, et al.
Publicado: (2020)