HIGHLIGHTS
- who: Noushin Hajarolasvadi from the Department of Visual, Germany have published the article: Volumetric macromolecule identification in cryo-electron tomograms using capsule networks, in the Journal: (JOURNAL)
- what: The main contributions of this study are two-fold: First, a deeper neural_network architecture is introduced that successfully performs multi-class and binary molecule identification on the test data. The main reason behind using dilated convolution is having a larger receptive field without extra computational cost.
- how: The experiments and visualization results show that the model performs successfully in both binary and multi-class macro . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.