Enhancing the accuracies by performing pooling decisions adjacent to the output layer

Learning classification tasks of [Formula: see text] inputs typically consist of [Formula: see text] ) max-pooling (MP) operators along the entire feedforward deep architecture. Here we show, using the CIFAR-10 database, that pooling decisions adjacent to the last convolutional layer significantly e...

Descripción completa

Detalles Bibliográficos
Autores principales: Meir, Yuval, Tzach, Yarden, Gross, Ronit D., Tevet, Ofek, Vardi, Roni, Kanter, Ido
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10471572/
https://www.ncbi.nlm.nih.gov/pubmed/37652973
http://dx.doi.org/10.1038/s41598-023-40566-y

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10471572/
https://www.ncbi.nlm.nih.gov/pubmed/37652973
http://dx.doi.org/10.1038/s41598-023-40566-y

Ejemplares similares