Number of necessary training examples for Neural Networks with different number of trainable parameters.

Götz, Th I; Göb, S; Sawant, S; Erick, X F; Wittenberg, T; Schmidkonz, C; Tomé, A M; Lang, E W; Ramming, A

Götz, Th I; Göb, S; Sawant, S; Erick, X F; Wittenberg, T; Schmidkonz, C; Tomé, A M; Lang, E W; Ramming, A.

Afiliación

Götz TI; Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany.
Göb S; Department of Internal Medicine 3, Rheumatology & Immunology, University Hospital Erlangen, Erlangen, Germany.
Sawant S; Department of Industrial Engineering and Health, Technical University of Applied Sciences Amberg-Weiden, Weiden, Germany.
Erick XF; Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany.
Wittenberg T; Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany.
Schmidkonz C; Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany.
Tomé AM; Fraunhofer IIS, Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany.
Lang EW; Clinic of Nuclear Medicine, University Hospital Erlangen, 91054 Erlangen, Germany.
Ramming A; Department of Industrial Engineering and Health, Technical University of Applied Sciences Amberg-Weiden, Weiden, Germany.

J Pathol Inform ; 13: 100114, 2022.

Article en En | MEDLINE | ID: mdl-36268092

Palabras clave

Cell segmentation; DNN complexity; Deep neural networks; Pruning; Training sample size

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Colección: 01-internacional Banco de datos: MEDLINE Idioma: En Revista: J Pathol Inform Año: 2022 Tipo del documento: Article País de afiliación: Alemania

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google