Deep learning framework for model reduction of dynamical systems
-
Updated
Dec 31, 2020 - Python
Deep learning framework for model reduction of dynamical systems
Simplified implementation of locally adaptive activation functions (LAAF) with slope recovery for deep and physics-informed neural networks (PINNs) in PyTorch.
Hydrodynamic image with the artificial lateral line using physics-informed informed neural networks and other proven methods in 2D dipole localization.
The lid-driven cavity is a popular problem within the field of computational fluid dynamics (CFD) for validating computational methods. In this repository, we will walk through the process of generating a 2D flow simulation for the Lid Driven Cavity (LDC) flow using Nvidia Modulus framework.
Efficient and Scalable Physics-Informed Deep Learning and Scientific Machine Learning on top of Tensorflow for multi-worker distributed computing
neural-network-based ROM testbed using an auto-encoder as an approximation manifold for the state, and an MLP for the reduced residual function
A simple Physics Informed Neural Network (PINN) implementation in TensorFlow 2 for magnetic field mapping using finite amount of magnetic field measurements.
Code to replicate experiments of paper "The role of adaptive activation functions in Fractional Physics-Informed Neural Networks""
This project used convolutional neural networks to predict the steady-state concentration of 3D porous media, and subsequently calculates the tortuosity. This package includes data generation, processing, training, and post-processing functions. The loss function includes a Laplacian loss, which is a physics-informed loss.
TF2 Implementation of Physics Informed Neural Networks and Neural Tangent Kernel
Here I will try to implement the solution of PDEs using PINN on pytorch for educational purpose
Interface machine learning with Cosmology and General Theory of relativity to visually analyze the evolution of GRS 1915+105 Black hole X-ray binary using WATCH ASM data captured aboard GRANAT.
[AAAI-23] Epidemiologically-informed Neural Networks
To address some of the failure modes in training of physics informed neural networks, a Lagrangian architecture is designed to conform to the direction of travel of information in convection-diffusion equations, i.e., method of characteristic; The repository includes a pytorch implementation of PINN and proposed LPINN with periodic boundary cond…
The code enables to perform Bayesian inference in an efficient manner through the use of Hamiltonian Neural Networks (HNNs), Deep Neural Networks (DNNs), Neural ODEs, and Symplectic Neural Networks (SympNets) used with state-of-the-art sampling schemes like Hamiltonian Monte Carlo (HMC) and the No-U-Turn-Sampler (NUTS).
Using Physics-Informed Deep Learning (PIDL) techniques (W-PINNs-DE & W-PINNs) to solve forward and inverse hydrodynamic shock-tube problems and plane stress linear elasticity boundary value problems
Using NVIDIA modulus for airfoil optimizations at different angles.
An application of PINN to SIR modeling
Add a description, image, and links to the physics-informed-neural-networks topic page so that developers can more easily learn about it.
To associate your repository with the physics-informed-neural-networks topic, visit your repo's landing page and select "manage topics."