CupNet -- Pruning a network for geometric data
arXiv:2005.05276 · doi:10.1007/978-3-030-86380-7_3
Abstract
Using data from a simulated cup drawing process, we demonstrate how the inherent geometrical structure of cup meshes can be used to effectively prune an artificial neural network in a straightforward way.
arXiv comment4 pages, 2 figures, 1 table
References in corpus (5)
- Scikit-learn: Machine Learning in Python
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Rethinking the Value of Network Pruning
- Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
- The Good, the Bad and the Ugly: Augmenting a black-box model with expert knowledge