Elettra-Sincrotrone Trieste S.C.p.A. website uses session cookies which are required for users to navigate appropriately and safely. Session cookies created by the Elettra-Sincrotrone Trieste S.C.p.A. website navigation do not affect users' privacy during their browsing experience on our website, as they do not entail processing their personal identification data. Session cookies are not permanently stored and indeed are cancelled when the connection to the Elettra-Sincrotrone Trieste S.C.p.A. website is terminated.
More info
OK

Deep neural networks for classifying complex features in diffraction images

This work provides a general introduction on the capabilities of neural networks and provide results on the first domain adaption of neural networks for the use case of diffraction images as input data. J. Zimmermann et al. Physical Review E 99, 063309 (2019)

Here we present the setup, our modifications, and the training process of the deep neural network for diffraction image classification and its systematic bench marking. We find that deep neural networks significantly outperform previous attempts for sorting and classifying complex diffraction patterns and are a significant improvement for the much-needed assistance during postprocessing of large amounts of experimental coherent diffraction imaging data.


Retrieve article

Zimmermann Julian, Langbehn Bruno, Cucini Riccardo, Di Fraia Michele, Finetti Paola, LaForge Aaron, Nishiyama Toshiyuki, Ovcharenko Yevheniy, Piseri Paolo, Plekan Oksana, Prince Kevin Charles, Stienkemeier Frank, Ueda Kiyoshi, Callegari Carlo, Moeller Thomas, Rupp Daniela
Physical Review E 99, 063309 (2019)
doi: 10.1103/PhysRevE.99.063309

Last Updated on Tuesday, 13 October 2020 15:58