2 papers
cs.CV2020
Utilizing a null class to restrict decision spaces and defend against neural network adversarial attacks
Matthew J. Roos
Despite recent progress, deep neural networks generally continue to be vulnerable to so-called adversarial examples--input images with small perturbations that can result in change…
q-bio.QM2017
Neural Reconstruction Integrity: A metric for assessing the connectivity of reconstructed neural networks
Elizabeth P. Reilly, Jeffrey S. Garretson, William Gray Roncal +4
Neuroscientists are actively pursuing high-precision maps, or graphs, consisting of networks of neurons and connecting synapses in mammalian and non-mammalian brains. Such graphs,…