no code implementations • 15 Aug 2022 • Wenceslao Shaw Cortez, Soumya Vasisht, Aaron Tuor, Ján Drgoňa, Draguna Vrabie
Conventional physics-based modeling is a time-consuming bottleneck in control design for complex nonlinear systems like autonomous underwater vehicles (AUVs).
1 code implementation • 3 Aug 2022 • Wenceslao Shaw Cortez, Jan Drgona, Aaron Tuor, Mahantesh Halappanavar, Draguna Vrabie
We develop a novel form of differentiable predictive control (DPC) with safety and robustness guarantees based on control barrier functions.
no code implementations • 11 Jul 2022 • James Koch, Zhao Chen, Aaron Tuor, Jan Drgona, Draguna Vrabie
Networked dynamical systems are common throughout science in engineering; e. g., biological networks, reaction networks, power systems, and the like.
no code implementations • 22 May 2022 • Sayak Mukherjee, Ján Drgoňa, Aaron Tuor, Mahantesh Halappanavar, Draguna Vrabie
We present a learning-based predictive control methodology using the differentiable programming framework with probabilistic Lyapunov-based stability guarantees.
no code implementations • 20 Mar 2022 • Shrirang Abhyankar, Jan Drgona, Andrew August, Elliot Skomski, Aaron Tuor
In this work, we investigate a data-driven approach for obtaining a reduced equivalent load model of distribution systems for electromechanical transient stability analysis.
1 code implementation • 16 Mar 2022 • Ethan King, Jan Drgona, Aaron Tuor, Shrirang Abhyankar, Craig Bakker, Arnab Bhattacharya, Draguna Vrabie
The dynamics-aware economic dispatch (DED) problem embeds low-level generator dynamics and operational constraints to enable near real-time scheduling of generation units in a power network.
1 code implementation • 2 Mar 2022 • Ján Drgoňa, Sayak Mukherjee, Aaron Tuor, Mahantesh Halappanavar, Draguna Vrabie
The problem of synthesizing stochastic explicit model predictive control policies is known to be quickly intractable even for systems of modest complexity when using classical control-theoretic methods.
no code implementations • 28 Feb 2022 • Aowabin Rahman, Ján Drgoňa, Aaron Tuor, Jan Strube
In particular, we present a quantitative study comparing NODE's performance against neural state-space models and classical linear system identification methods.
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 • 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.
no code implementations • 26 Nov 2020 • Jan Drgona, Soumya Vasisht, Aaron Tuor, Draguna Vrabie
In this paper, we provide sufficient conditions for dissipativity and local asymptotic stability of discrete-time dynamical systems parametrized by deep neural networks.
no code implementations • 7 Nov 2020 • Jan Drgona, Karol Kis, Aaron Tuor, Draguna Vrabie, Martin Klauco
In the DPC framework, a neural state-space model is learned from time-series measurements of the system dynamics.
no code implementations • 23 Sep 2020 • Henry Kvinge, Zachary New, Nico Courts, Jung H. Lee, Lauren A. Phillips, Courtney D. Corley, Aaron Tuor, Andrew Avila, Nathan O. Hodas
Few-shot learning algorithms, which seek to address this limitation, are designed to generalize well to new tasks with limited data.
no code implementations • 24 Apr 2020 • Loc Truong, Chace Jones, Brian Hutchinson, Andrew August, Brenda Praggastis, Robert Jasper, Nicole Nichols, Aaron Tuor
First, the success rate of backdoor poisoning attacks varies widely, depending on several factors, including model architecture, trigger pattern and regularization technique.
2 code implementations • 23 Apr 2020 • Jan Drgona, Aaron Tuor, Draguna Vrabie
We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees.
1 code implementation • ICLR Workshop DeepDiffEq 2019 • Aaron Tuor, Jan Drgona, Draguna Vrabie
Differential equations are frequently used in engineering domains, such as modeling and control of industrial systems, where safety and performance guarantees are of paramount importance.
no code implementations • 17 Feb 2019 • Aaron Tuor, Fnu Anubhav, Lauren Charles
Due to globalization, geographic boundaries no longer serve as effective shields for the spread of infectious diseases.
no code implementations • 13 Mar 2018 • Andy Brown, Aaron Tuor, Brian Hutchinson, Nicole Nichols
Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and malware detection.
1 code implementation • 2 Dec 2017 • Aaron Tuor, Ryan Baerwolf, Nicolas Knowles, Brian Hutchinson, Nicole Nichols, Rob Jasper
By treating system logs as threads of interleaved "sentences" (event log lines) to train online unsupervised neural network language models, our approach provides an adaptive model of normal network behavior.
1 code implementation • 2 Oct 2017 • Aaron Tuor, Samuel Kaplan, Brian Hutchinson, Nicole Nichols, Sean Robinson
As a prospective filter for the human analyst, we present an online unsupervised deep learning approach to detect anomalous network activity from system logs in real time.