no code implementations • 9 Sep 2022 • Brian S. Robinson, Clare W. Lau, Alexander New, Shane M. Nichols, Erik C. Johnson, Michael Wolmetz, William G. Coon
While some catastrophic forgetting persisted over the course of network training, higher levels of synaptic downscaling lead to better retention of early tasks and further facilitated the recovery of early task accuracy during subsequent training.
1 code implementation • 31 Jan 2018 • Marc Bosch, Christopher M. Gifford, Austin G. Dress, Clare W. Lau, Jeffrey G. Skibo, Gordon A. Christie
We scan the segmentation parameter space and generate a collection of image segmentation hypotheses (from highly over-segmented to under-segmented).