2 code implementations • 21 Jun 2023 • Kaushik Bhattacharya, Nikola Kovachki, Aakila Rajan, Andrew M. Stuart, Margaret Trautner
However, a major challenge in data-driven learning approaches for this problem has remained unexplored: the impact of discontinuities and corner interfaces in the underlying material.
1 code implementation • 19 Aug 2021 • Nikola Kovachki, Zongyi Li, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
The classical development of neural networks has primarily focused on learning mappings between finite dimensional Euclidean spaces or finite sets.
2 code implementations • 13 Jun 2021 • Zongyi Li, Miguel Liu-Schiaffini, Nikola Kovachki, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
Chaotic systems are notoriously challenging to predict because of their sensitivity to perturbations and errors due to time stepping.
no code implementations • 23 Dec 2020 • Victoria Lee, Kaushik Bhattacharya
Nematic elastomers are programmable soft materials that display large, reversible and predictable deformation under an external stimulus such as a change in temperature or light.
Soft Condensed Matter
no code implementations • 2 Dec 2020 • Ruobing Bai, Eric Ocegueda, Kaushik Bhattacharya
We find that the photo-reaction rate depends sensitively on temperature: at temperatures below the crystal-melt transition temperature, photoreaction is collective, requires a critical light intensity and shows an abrupt first order phase transition manifesting nucleation and growth; at temperatures above the transition temperature, photoreaction is independent and follows first order kinetics.
Soft Condensed Matter Mesoscale and Nanoscale Physics
no code implementations • 2 Nov 2020 • Ruobing Bai, Ying Shi Teh, Kaushik Bhattacharya
There is current interest in developing photoactive materials that deform on illumination and can thus be used for photomechanical actuation.
Mesoscale and Nanoscale Physics Soft Condensed Matter Statistical Mechanics
17 code implementations • ICLR 2021 • Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces.
4 code implementations • NeurIPS 2020 • Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
One of the main challenges in using deep learning-based methods for simulating physical systems and solving partial differential equations (PDEs) is formulating physics-based data in the desired structure for neural networks.
no code implementations • 7 May 2020 • Kaushik Bhattacharya, Bamdad Hosseini, Nikola B. Kovachki, Andrew M. Stuart
We develop a general framework for data-driven approximation of input-output maps between infinite-dimensional spaces.
6 code implementations • ICLR Workshop DeepDiffEq 2019 • Zongyi Li, Nikola Kovachki, Kamyar Azizzadenesheli, Burigede Liu, Kaushik Bhattacharya, Andrew Stuart, Anima Anandkumar
The classical development of neural networks has been primarily for mappings between a finite-dimensional Euclidean space and a set of classes, or between two finite-dimensional Euclidean spaces.