no code implementations • 22 Dec 2023 • Riccardo Scodellaro, Ajinkya Kulkarni, Frauke Alves, Matthias Schröter
The training of these CNNs, and in fact of all deep neural network architectures, uses the backpropagation algorithm where the output of the network is compared with the desired result and the difference is then used to tune the weights of the network towards the desired outcome.
1 code implementation • 10 Mar 2017 • Simon Weis, Philipp W. A. Schönhöfer, Fabian M. Schaller, Matthias Schröter, Gerd E. Schröder-Turk
It directly supports common particle shapes and offers a generic mode, which allows to deal with any type of particles that can be described mathematically.
Data Analysis, Statistics and Probability Soft Condensed Matter Computational Physics