Search Results - "Trask, Nathaniel A."

A physics-informed operator regression framework for extracting data-driven continuum models by Patel, Ravi G., Trask, Nathaniel A., Wood, Mitchell A., Cyr, Eric C.

“…The application of deep learning toward discovery of data-driven models requires careful application of inductive biases to obtain a description of physics…”
Get full text

Thermodynamically consistent physics-informed neural networks for hyperbolic systems by Patel, Ravi G., Manickam, Indu, Trask, Nathaniel A., Wood, Mitchell A., Lee, Myoungkyu, Tomas, Ignacio, Cyr, Eric C.

“…•Spacetime control volume PINN reformulation naturally handles IC/BC and conservation.•Novel biases for entropy consistency and TVD provide robust DNN modeling…”
Get full text

Asymptotically compatible reproducing kernel collocation and meshfree integration for the peridynamic Navier equation by Leng, Yu, Tian, Xiaochuan, Trask, Nathaniel A., Foster, John T.

“…In this work, we study reproducing kernel (RK) collocation method for peridynamic Navier equation. In the first part, we apply a linear RK approximation to…”
Get full text

Accurate Compression of Tabulated Chemistry Models with Partition of Unity Networks by Armstrong, Elizabeth, Hansen, Michael A., Knaus, Robert C., Trask, Nathaniel A., Hewson, John C., Sutherland, James C.

“…Tabulated chemistry models are widely used to simulate large-scale turbulent fires in applications including energy generation and fire safety. Tabulation via…”
Get full text

Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter by Villarreal, Ruben, Vlassis, Nikolaos N., Phan, Nhon N., Catanach, Tommie A., Jones, Reese E., Trask, Nathaniel A., Kramer, Sharlotte L. B., Sun, WaiChing

“…Experimental data are often costly to obtain, which makes it difficult to calibrate complex models. For many models an experimental design that produces the…”
Get full text

Asymptotically compatible reproducing kernel collocation and meshfree integration for the peridynamic Navier equation by Leng, Yu, Tian, Xiaochuan, Trask, Nathaniel A., Foster, John T.

“…Here, we study reproducing kernel (RK) collocation method for peridynamic Navier equation. In the first part, we apply a linear RK approximation to both…”
Get full text

Accurate Compression of Tabulated Chemistry Models with Partition of Unity Networks by Armstrong, Elizabeth, Hansen, Michael A., Knaus, Robert C., Trask, Nathaniel A., Hewson, John C., Sutherland, James C.

“…Tabulated chemistry models are widely used to simulate large-scale turbulent fires in applications including energy generation and fire safety. Tabulation via…”
Get full text

Machine learning structure preserving brackets for forecasting irreversible processes by Lee, Kookjin, Trask, Nathaniel A, Stinis, Panos

“…Forecasting of time-series data requires imposition of inductive biases to obtain predictive extrapolation, and recent works have imposed…”
Get full text

Asymptotically compatible reproducing kernel collocation and meshfree integration for the peridynamic Navier equation by Leng, Yu, Tian, Xiaochuan, Trask, Nathaniel A, Foster, John T

“…In this work, we study the reproducing kernel (RK) collocation method for the peridynamic Navier equation. We first apply a linear RK approximation on both…”
Get full text

Parallel implementation of a compatible high-order meshless method for the Stokes' equations by Ha, Quang-Thinh, Kuberry, Paul A, Trask, Nathaniel A, Ryan, Emily M

“…A parallel implementation of a compatible discretization scheme for steady-state Stokes problems is presented in this work. The scheme uses generalized moving…”
Get full text

Partition of unity networks: deep hp-approximation by Lee, Kookjin, Trask, Nathaniel A, Patel, Ravi G, Gulian, Mamikon A, Cyr, Eric C

“…Approximation theorists have established best-in-class optimal approximation rates of deep neural networks by utilizing their ability to simultaneously emulate…”
Get full text

Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter by Villarreal, Ruben, Vlassis, Nikolaos N, Phan, Nhon N, Catanach, Tommie A, Jones, Reese E, Trask, Nathaniel A, Kramer, Sharlotte L. B, Sun, WaiChing

“…Experimental data is costly to obtain, which makes it difficult to calibrate complex models. For many models an experimental design that produces the best…”
Get full text

A physics-informed operator regression framework for extracting data-driven continuum models by Patel, Ravi G, Trask, Nathaniel A, Wood, Mitchell A, Cyr, Eric C

“…The application of deep learning toward discovery of data-driven models requires careful application of inductive biases to obtain a description of physics…”
Get full text

A block coordinate descent optimizer for classification problems exploiting convexity by Patel, Ravi G, Trask, Nathaniel A, Gulian, Mamikon A, Cyr, Eric C

“…Second-order optimizers hold intriguing potential for deep learning, but suffer from increased cost and sensitivity to the non-convexity of the loss surface as…”
Get full text

Thermodynamically consistent physics-informed neural networks for hyperbolic systems by Patel, Ravi G, Manickam, Indu, Trask, Nathaniel A, Wood, Mitchell A, Lee, Myoungkyu, Tomas, Ignacio, Cyr, Eric C

“…Physics-informed neural network architectures have emerged as a powerful tool for developing flexible PDE solvers which easily assimilate data, but face…”
Get full text

Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint by Cyr, Eric C, Gulian, Mamikon A, Patel, Ravi G, Perego, Mauro, Trask, Nathaniel A

“…Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve…”
Get full text