no code implementations • 20 Mar 2024 • Abhinab Bhattacharjee, Andrey A. Popov, Arash Sarshar, Adrian Sandu
The Adam optimizer, often used in Machine Learning for neural network training, corresponds to an underlying ordinary differential equation (ODE) in the limit of very small learning rates.
no code implementations • 25 Dec 2023 • Adwait Verulkar, Corina Sandu, Adrian Sandu, Daniel Dopico
This work addresses the gradient-based optimization methodology for multibody dynamic systems with joint friction using a direct sensitivity approach for gradient computation.
no code implementations • 23 Aug 2023 • Ali Haisam Muhammad Rafid, Adrian Sandu
A neural network architecture that incorporates feedback control, named Feedback Neural Networks, is proposed.
no code implementations • 29 May 2023 • Ali Haisam Muhammad Rafid, Adrian Sandu
Regularization techniques such as $\mathcal{L}_1$ and $\mathcal{L}_2$ regularizers are effective in sparsifying neural networks (NNs).
no code implementations • 14 Jul 2022 • Andrey A. Popov, Arash Sarshar, Austin Chennault, Adrian Sandu
A rapidly growing area of research is the use of machine learning approaches such as autoencoders for dimensionality reduction of data and models in scientific applications.
2 code implementations • 6 May 2022 • Jostein Barry-Straume, Arash Sarshar, Andrey A. Popov, Adrian Sandu
A fundamental problem in science and engineering is designing optimal control policies that steer a given system towards a desired outcome.
no code implementations • 16 Nov 2021 • Austin Chennault, Andrey A. Popov, Amit N. Subrahmanya, Rachel Cooper, Ali Haisam Muhammad Rafid, Anuj Karpatne, Adrian Sandu
Surrogates constructed using adjoint information demonstrate superior performance on the 4D-Var data assimilation problem compared to a standard neural network surrogate that uses only forward dynamics information.
no code implementations • 27 Aug 2021 • Rachel Cooper, Andrey A. Popov, Adrian Sandu
Reduced order modeling (ROM) is a field of techniques that approximates complex physics-based models of real-world processes by inexpensive surrogates that capture important dynamical characteristics with a smaller number of degrees of freedom.
no code implementations • 25 Feb 2021 • Andrey A Popov, Adrian Sandu
The multifidelity ensemble Kalman filter (MFEnKF) recently developed by the authors combines a full-order physical model and a hierarchy of reduced order surrogate models in order to increase the computational efficiency of data assimilation.
no code implementations • 29 Feb 2020 • Andrey A Popov, Adrian Sandu, Elias D. Nino-Ruiz, Geir Evensen
The Ensemble Kalman Filters (EnKF) employ a Monte-Carlo approach to represent covariance information, and are affected by sampling errors in operational settings where the number of model realizations is much smaller than the model state dimension.
Methodology Numerical Analysis Numerical Analysis
no code implementations • 2 Jan 2018 • Azam Moosavi, Ahmed Attia, Adrian Sandu
In typical weather forecasting applications, the model state space has dimension $10^{9}-10^{12}$, while the ensemble size typically ranges between $30-100$ members.
no code implementations • 9 Nov 2015 • Azam Moosavi, Razvan Stefanescu, Adrian Sandu
Reduced order models are computationally inexpensive approximations that capture the important dynamical characteristics of large, high-fidelity computer models of physical systems.