no code implementations • 20 Nov 2020 • Tom Grimes, Eric Church, William Pitts, Lynn Wood, Eva Brayfindley, Luke Erikson, Mark Greaves
For this example, the effect of the robust and domain adversarial training is to remove features indicative of the difference in background between instances of operation of the device - providing highly discriminative features on which to construct the classifier.
no code implementations • 4 Sep 2020 • Tom Grimes, Eric Church, William Pitts, Lynn Wood
By applying LIME to this classifier and aggregating the results over many classifications for the same device, it was possible to determine the frequency bands used by the classifier to make decisions.