Similarity-based pairing improves efficiency of siamese neural networks for regression tasks and uncertainty quantification

Siamese networks, representing a novel class of neural networks, consist of two identical subnetworks sharing weights but receiving different inputs. Here we present a similarity-based pairing method for generating compound pairs to train Siamese neural networks for regression tasks. In comparison w...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Yumeng, Menke, Janosch, He, Jiazhen, Nittinger, Eva, Tyrchan, Christian, Koch, Oliver, Zhao, Hongtao
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer International Publishing 2023
Materias:
Research
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10469421/
https://www.ncbi.nlm.nih.gov/pubmed/37649050
http://dx.doi.org/10.1186/s13321-023-00744-6

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10469421/
https://www.ncbi.nlm.nih.gov/pubmed/37649050
http://dx.doi.org/10.1186/s13321-023-00744-6

Ejemplares similares