2 citations · 3 across the 6 of their papers we have counts for
7 papers
Robust Geospatial Coordination of Multi-Agent Communications Networks Under Attrition
Jonathan S. Kent, Eliana Stefani, Brian Plancher
Coordinating emergency responses in extreme environments, such as wildfires, requires resilient and high-bandwidth communication backbones. While autonomous aerial swarms can estab…
A Technical Note on the Architectural Effects on Maximum Dependency Lengths of Recurrent Neural Networks
Jonathan S. Kent, Michael M. Murray
This work proposes a methodology for determining the maximum dependency length of a recurrent neural network (RNN), and then studies the effects of architectural changes, including…
Designing with Non-Finite Output Dimension via Fourier Coefficients of Neural Waveforms
Jonathan S. Kent
Ordinary Deep Learning models require having the dimension of their outputs determined by a human practitioner prior to training and operation. For design tasks, this places a hard…
Chaos Theory and Adversarial Robustness
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. This paper uses ide…
Indecision Trees: Learning Argument-Based Reasoning under Quantified Uncertainty
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 singl…
DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
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. One, they do not typically generalize well outside of the distr…
Unsupervised Learning for Target Tracking and Background Subtraction in Satellite Imagery
Jonathan S. Kent, Charles C. Wamsley, Davin Flateau +1
This paper describes an unsupervised machine learning methodology capable of target tracking and background suppression via a novel dual-model approach. ``Jekyll`` produces a video…