no code implementations • 22 Nov 2021 • Jung H Lee, Henry J Kvinge, Scott Howland, Zachary New, John Buckheit, Lauren A. Phillips, Elliott Skomski, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas
Our empirical evaluations suggest that ATL can help DL models learn more efficiently, especially when available examples are limited.
no code implementations • 25 Jul 2021 • Jan Drgona, Aaron Tuor, Soumya Vasisht, Elliott Skomski, Draguna Vrabie
We present a differentiable predictive control (DPC) methodology for learning constrained control laws for unknown nonlinear systems.
no code implementations • 2 Jun 2021 • Henry Kvinge, Scott Howland, Nico Courts, Lauren A. Phillips, John Buckheit, Zachary New, Elliott Skomski, Jung H. Lee, Sandeep Tiwari, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas
We describe how this problem is subtly different from out-of-distribution detection and describe a new method of identifying OOS examples within the Prototypical Networks framework using a fixed point which we call the generic representation.
no code implementations • 8 Apr 2021 • Elliott Skomski, Aaron Tuor, Andrew Avila, Lauren Phillips, Zachary New, Henry Kvinge, Courtney D. Corley, Nathan Hodas
Recently proposed few-shot image classification methods have generally focused on use cases where the objects to be classified are the central subject of images.
no code implementations • 6 Jan 2021 • Elliott Skomski, Soumya Vasisht, Colby Wight, Aaron Tuor, Jan Drgona, Draguna Vrabie
Neural network modules conditioned by known priors can be effectively trained and combined to represent systems with nonlinear dynamics.
no code implementations • 26 Nov 2020 • Elliott Skomski, Jan Drgona, Aaron Tuor
Recent works exploring deep learning application to dynamical systems modeling have demonstrated that embedding physical priors into neural networks can yield more effective, physically-realistic, and data-efficient models.