Two-dimensional materials-based probabilistic synapses and reconfigurable neurons for measuring inference uncertainty using Bayesian neural networks

Artificial neural networks have demonstrated superiority over traditional computing architectures in tasks such as pattern classification and learning. However, they do not measure uncertainty in predictions, and hence they can make wrong predictions with high confidence, which can be detrimental fo...

Descripción completa

Detalles Bibliográficos
Autores principales: Sebastian, Amritanand, Pendurthi, Rahul, Kozhakhmetov, Azimkhan, Trainor, Nicholas, Robinson, Joshua A., Redwing, Joan M., Das, Saptarshi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group UK 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576759/
https://www.ncbi.nlm.nih.gov/pubmed/36253370
http://dx.doi.org/10.1038/s41467-022-33699-7

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9576759/
https://www.ncbi.nlm.nih.gov/pubmed/36253370
http://dx.doi.org/10.1038/s41467-022-33699-7

Ejemplares similares