no code implementations • 28 Jan 2021 • Deborah Weeks, Samuel Rivera
While these methods typically require large amounts of labeled training data, domain adaptation (DA) or transfer learning (TL) enables these algorithms to transfer knowledge from a labelled (source) data set to an unlabelled but related (target) data set of interest.
no code implementations • 22 Dec 2020 • Samuel Rivera, Joel Klipfel, Deborah Weeks
We also provide practical guidelines for training the network while overcoming vanishing gradients which inhibit learning in some adversarial training settings.