activity
20192021
most citedRobust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint

17 citations · 24 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG20216 cited

Partition of unity networks: deep hp-approximation

Kookjin Lee, Nathaniel A. Trask, Ravi G. Patel +2

Approximation theorists have established best-in-class optimal approximation rates of deep neural networks by utilizing their ability to simultaneously emulate partitions of unity…

math.NA20201 cited

Thermodynamically consistent physics-informed neural networks for hyperbolic systems

Ravi G. Patel, Indu Manickam, Nathaniel A. Trask +4

Physics-informed neural network architectures have emerged as a powerful tool for developing flexible PDE solvers which easily assimilate data, but face challenges related to the P…

physics.comp-ph2020

A physics-informed operator regression framework for extracting data-driven continuum models

Ravi G. Patel, Nathaniel A. Trask, Mitchell A. Wood +1

The application of deep learning toward discovery of data-driven models requires careful application of inductive biases to obtain a description of physics which is both accurate a…

cs.LG2020

A block coordinate descent optimizer for classification problems exploiting convexity

Ravi G. Patel, Nathaniel A. Trask, Mamikon A. Gulian +1

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 compared to gradient…

math.NA2020

Asymptotically compatible reproducing kernel collocation and meshfree integration for the peridynamic Navier equation

Yu Leng, Xiaochuan Tian, Nathaniel A. Trask +1

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 displacements and dilata…

cs.LG201917 cited

Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint

Eric C. Cyr, Mamikon A. Gulian, Ravi G. Patel +2

Motivated by the gap between theoretical optimal approximation rates of deep neural networks (DNNs) and the accuracy realized in practice, we seek to improve the training of DNNs.…