no code implementations • 10 Apr 2023 • Jonathan Wittmer, Jacob Badger, Hari Sundar, Tan Bui-Thanh
In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing both the time-to-solution and memory requirements.
no code implementations • 13 Nov 2022 • C G Krishnanunni, Tan Bui-Thanh
We derive the necessary conditions for trainability of a newly added layer and analyze the role of manifold regularization.
no code implementations • 9 Aug 2022 • Hai V. Nguyen, Tan Bui-Thanh
Real-time accurate solutions of large-scale complex dynamical systems are in critical need for control, optimization, uncertainty quantification, and decision-making in practical engineering and science applications, especially digital twin applications.
no code implementations • 30 Dec 2021 • Tan Bui-Thanh
This paper is the first effort to provide a unified and constructive framework for the universality of a large class of activation functions including most of existing ones.
no code implementations • 25 May 2021 • Hai V. Nguyen, Tan Bui-Thanh
This is the strength of DL but also one of its key limitations when applied to science and engineering problems in which underlying physical properties and desired accuracy need to be achieved.
no code implementations • 14 Dec 2020 • Sriramkrishnan Muralikrishnan, Stephen Shannon, Tan Bui-Thanh, John N. Shadid
Additionally for the upper block a preliminary study of an alternate nodal block system solver based on a multilevel approximate nested dissection is presented.
Numerical Analysis Numerical Analysis Computational Physics Plasma Physics
no code implementations • 17 Dec 2019 • Sheroze Sheriffdeen, Jean C. Ragusa, Jim E. Morel, Marvin L. Adams, Tan Bui-Thanh
In this paper, we propose to enlarge the validity of ROMs and hence improve the accuracy outside the reduced subspaces by incorporating a data-driven ML technique.
no code implementations • 5 Dec 2019 • Hwan Goh, Sheroze Sheriffdeen, Jonathan Wittmer, Tan Bui-Thanh
Further, this framework possesses an inherent adaptive optimization property that emerges through the learning of the posterior uncertainty.