no code implementations • 5 Sep 2023 • Chayan Banerjee, Kien Nguyen, Clinton Fookes, Maziar Raissi
We present a thorough review of the literature on incorporating physics information, as known as physics priors, in reinforcement learning approaches, commonly referred to as physics-informed reinforcement learning (PIRL).
no code implementations • 31 Jan 2023 • Mahdieh Yazdani, Maziar Raissi
Our proposed algorithm uses a combination of machine learning, computer vision and hedonic pricing models trained on real estate data to estimate the value of a given property.
no code implementations • 30 Jan 2023 • Sukirt Thakur, Maziar Raissi, Harsa Mitra, Arezoo Ardekani
This paper proposes a method for scaling the mean squared loss terms in the objective function used to train PINNs.
1 code implementation • 26 Jan 2023 • Maziar Raissi
This work formulates the machine learning mechanism as a bi-level optimization problem.
no code implementations • 14 Nov 2022 • Salah A Faroughi, Nikhil Pawar, Celio Fernandes, Maziar Raissi, Subasish Das, Nima K. Kalantari, Seyed Kourosh Mahjour
This study aims to present a review of the four neural network frameworks (i. e., PgNNs, PiNNs, PeNNs, and NOs) used in scientific computing research.
2 code implementations • 14 Jan 2022 • Salvatore Cuomo, Vincenzo Schiano di Cola, Fabio Giampaolo, Gianluigi Rozza, Maziar Raissi, Francesco Piccialli
Physics-Informed Neural Networks (PINN) are neural networks (NNs) that encode model equations, like Partial Differential Equations (PDE), as a component of the neural network itself.
1 code implementation • 11 Oct 2021 • Sagi Shaier, Maziar Raissi, Padmanabhan Seshaiyer
This approach builds on a successful physics informed neural network approaches that have been applied to a variety of applications that can be modeled by linear and non-linear ordinary and partial differential equations.
1 code implementation • 14 Feb 2020 • Ehsan Haghighat, Maziar Raissi, Adrian Moure, Hector Gomez, Ruben Juanes
We also show the applicability of the framework for transfer learning, and find vastly accelerated convergence during network re-training.
1 code implementation • 26 Aug 2018 • Maziar Raissi, Zhicheng Wang, Michael S. Triantafyllou, George Em. Karniadakis
Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered information on the velocity field.
1 code implementation • 13 Aug 2018 • Maziar Raissi, Alireza Yazdani, George Em. Karniadakis
We present hidden fluid mechanics (HFM), a physics informed deep learning framework capable of encoding an important class of physical laws governing fluid motions, namely the Navier-Stokes equations.
no code implementations • 2 Aug 2018 • Mamikon Gulian, Maziar Raissi, Paris Perdikaris, George Karniadakis
We extend this framework to linear space-fractional differential equations.
3 code implementations • 19 Apr 2018 • Maziar Raissi
Classical numerical methods for solving partial differential equations suffer from the curse dimensionality mainly due to their reliance on meticulously generated spatio-temporal grids.
4 code implementations • 20 Jan 2018 • Maziar Raissi
A long-standing problem at the interface of artificial intelligence and applied mathematics is to devise an algorithm capable of achieving human level or even superhuman proficiency in transforming observed data into predictive mathematical models of the physical world.
2 code implementations • 4 Jan 2018 • Maziar Raissi, Paris Perdikaris, George Em. Karniadakis
The process of transforming observed data into predictive mathematical models of the physical world has always been paramount in science and engineering.
29 code implementations • 28 Nov 2017 • Maziar Raissi, Paris Perdikaris, George Em. Karniadakis
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations.
23 code implementations • 28 Nov 2017 • Maziar Raissi, Paris Perdikaris, George Em. Karniadakis
We introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given law of physics described by general nonlinear partial differential equations.
1 code implementation • 2 Aug 2017 • Maziar Raissi, George Em. Karniadakis
While there is currently a lot of enthusiasm about "big data", useful data is usually "small" and expensive to acquire.
1 code implementation • 11 Apr 2017 • Maziar Raissi
This work introduces the concept of parametric Gaussian processes (PGPs), which is built upon the seemingly self-contradictory idea of making Gaussian processes parametric.
1 code implementation • 29 Mar 2017 • Maziar Raissi, Paris Perdikaris, George Em. Karniadakis
Numerical Gaussian processes, by construction, are designed to deal with cases where: (1) all we observe are noisy data on black-box initial conditions, and (2) we are interested in quantifying the uncertainty associated with such noisy data in our solutions to time-dependent partial differential equations.
2 code implementations • 10 Jan 2017 • Maziar Raissi, George Em. Karniadakis
This work leverages recent advances in probabilistic machine learning to discover conservation laws expressed by parametric linear equations.
1 code implementation • 16 Jul 2016 • Maziar Raissi, Paris Perdikaris, George Em. Karniadakis
For more than two centuries, solutions of differential equations have been obtained either analytically or numerically based on typically well-behaved forcing and boundary conditions for well-posed problems.
1 code implementation • 26 Apr 2016 • Maziar Raissi, George Karniadakis
We develop a novel multi-fidelity framework that goes far beyond the classical AR(1) Co-kriging scheme of Kennedy and O'Hagan (2000).