no code implementations • 20 Oct 2022 • Jonathan S. Kent
Neural networks, being susceptible to adversarial attacks, should face a strict level of scrutiny before being deployed in critical or adversarial applications.
no code implementations • 17 Aug 2022 • Jonathan S. Kent
Ordinary Deep Learning models require having the dimension of their outputs determined by a human practitioner prior to training and operation.
no code implementations • 23 Jun 2022 • Jonathan S. Kent, David H. Menager
Using Machine Learning systems in the real world can often be problematic, with inexplicable black-box models, the assumed certainty of imperfect measurements, or providing a single classification instead of a probability distribution.
no code implementations • 27 Sep 2021 • Jonathan S. Kent, Bo Li
Deep Learning models possess two key traits that, in combination, make their use in the real world a risky prospect.
no code implementations • 13 Aug 2021 • Jonathan S. Kent, Charles C. Wamsley, Davin Flateau, Amber Ferguson
This paper describes an unsupervised machine learning methodology capable of target tracking and background suppression via a novel dual-model approach.