no code implementations • 22 Mar 2024 • Mehdi Shishehbor, Shirin Hosseinmardi, Ramin Bostanabad
Deep neural networks (DNNs) are increasingly used to solve partial differential equations (PDEs) that naturally arise while modeling a wide range of systems and physical phenomena.
no code implementations • 7 Jan 2024 • Carlos Mora, Amin Yousefpour, Shirin Hosseinmardi, Ramin Bostanabad
Physics-informed machine learning (PIML) has emerged as a promising alternative to conventional numerical methods for solving partial differential equations (PDEs).
1 code implementation • 12 Dec 2023 • Amin Yousefpour, Zahra Zanjani Foumani, Mehdi Shishehbor, Carlos Mora, Ramin Bostanabad
In this paper we introduce GP+, an open-source library for kernel-based learning via Gaussian processes (GPs) which are powerful statistical models that are completely characterized by their parametric covariance and mean functions.
no code implementations • 27 Oct 2023 • Jonathan Tammer Eweis-Labolle, Chuanning Zhao, Yoonjin Won, Ramin Bostanabad
We address these challenges by developing a data-driven framework for designing optimal porous microstructures for cooling applications.
no code implementations • 6 Sep 2023 • Zahra Zanjani Foumani, Amin Yousefpour, Mehdi Shishehbor, Ramin Bostanabad
In this paper, we dispense with these incorrect assumptions by proposing an MF emulation method that (1) learns a noise model for each data source, and (2) enables MFBO to leverage highly biased LF sources which are only locally correlated with the HF source.
no code implementations • 28 Aug 2023 • Arthur Feeney, Zitong Li, Ramin Bostanabad, Aparna Chandramowlishwaran
Mosaic Flow is a novel domain decomposition method designed to scale physics-informed neural PDE solvers to large domains.
no code implementations • 15 Jun 2023 • Amin Yousefpour, Mehdi Shishehbor, Zahra Zanjani Foumani, Ramin Bostanabad
Anomalies are samples that significantly deviate from the rest of the data and their detection plays a major role in building machine learning models that can be reliably used in applications such as data-driven design and novelty detection.
1 code implementation • 30 Jan 2023 • Carlos Mora, Jonathan Tammer Eweis-Labolle, Tyler Johnson, Likith Gadde, Ramin Bostanabad
Our NN architecture inversely learns non-trivial (e. g., non-additive and non-hierarchical) biases of the LF sources in an interpretable and visualizable manifold where each data source is encoded via a low-dimensional distribution.
1 code implementation • 4 Nov 2022 • Zahra Zanjani Foumani, Mehdi Shishehbor, Amin Yousefpour, Ramin Bostanabad
Bayesian optimization (BO) is increasingly employed in critical applications such as materials design and drug discovery.
no code implementations • 4 Dec 2021 • Nicholas Oune, Jonathan Tammer Eweis-Labolle, Ramin Bostanabad
Multi-fidelity modeling and calibration are data fusion tasks that ubiquitously arise in engineering design.
no code implementations • 22 Apr 2021 • Hengjie Wang, Robert Planas, Aparna Chandramowlishwaran, Ramin Bostanabad
Then, we proposed mosaic flow(MF) predictor, a novel iterative algorithm that assembles the GFNet's inferences for BVPs on large domains with unseen sizes/shapes and BCs while preserving the spatial regularity of the solution.
no code implementations • 7 Feb 2021 • Nicholas Oune, Ramin Bostanabad
In this paper, we introduce latent map Gaussian processes (LMGPs) that inherit the attractive properties of GPs and are also applicable to mixed data which have both quantitative and qualitative inputs.