Decontextualized learning for interpretable hierarchical representations of visual patterns

Apart from discriminative modeling, the application of deep convolutional neural networks to basic research utilizing natural imaging data faces unique hurdles. Here, we present decontextualized hierarchical representation learning (DHRL), designed specifically to overcome these limitations. DHRL en...

Descripción completa

Detalles Bibliográficos
Autores principales: Etheredge, Robert Ian, Schartl, Manfred, Jordan, Alex
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7892362/
https://www.ncbi.nlm.nih.gov/pubmed/33659910
http://dx.doi.org/10.1016/j.patter.2020.100193

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7892362/
https://www.ncbi.nlm.nih.gov/pubmed/33659910
http://dx.doi.org/10.1016/j.patter.2020.100193

Ejemplares similares