Rahul Sundar's repositories
Applied-Deep-Learning
Applied Deep Learning Course
characterizing-pinns-failure-modes
Characterizing possible failure modes in physics-informed neural networks.
aa_autoencoder_mca
Supporting code for "reduced order modeling using advection-aware autoencoders"
awesome-network-analysis
A curated list of awesome network analysis resources.
best-of-streamlit
🏆 A ranked gallery of awesome streamlit apps built by the community
Conservative_PINNs
We propose a conservative physics-informed neural network (cPINN) on decompose domains for nonlinear conservation laws. The conservation property of cPINN is obtained by enforcing the flux continuity in the strong form along the sub-domain interfaces.
deeponet-fno
DeepONet & FNO (with practical extensions)
generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
gpinn
gPINN: Gradient-enhanced physics-informed neural networks
ModalPINN_Python_code
Publication of Python code used to train ModalPINN
multifidelity-deeponet
Multifidelity DeepONet
Natural-climate-reconstruction-with-VAE
Final project for the course Laboratory of Computational Physics mod. B, master degree in Physics of Data
PB-GAN
Physics-based regularization using generative adversarial networks
piDMD
MATLAB codes for physics-informed dynamic mode decomposition (piDMD)
PINN-for-Poisson-Equation
This repo contains the code for solving Poisson Equation using Physics Informed Neural Networks
PINNpapers_revised
Must-read Papers on Physics-Informed Neural Networks.
pytorch-vae-simple
A Variational Autoencoder (VAE) implemented in PyTorch
rang_pinn
Code for reproducing the paper: RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks
Rowdy_Activation_Functions
We propose Deep Kronecker Neural Network, which is a general framework for neural networks with adaptive activation functions. In particular we proposed Rowdy activation functions that inject sinusoidal fluctuations thereby allows the optimizer to exploit more and train the network faster. Various test cases ranging from function approximation, inferring the PDE solution, and the standard deep learning benchmarks like MNIST, CIFAR-10, CIFAR-100, SVHN etc are solved to show the efficacy of the proposed activation functions.
tfc
The Theory of Functional Connections: A functional interpolation method with applications in solving differential equations.
vae_mhd_solver
Variational Autoencoder (VAE)-like neural network to solve ideal MHD equilibrium in a tokamak
XPINNs
Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations
XPINNs_TensorFlow-2
XPINN code written in TensorFlow 2 (2x to 3x times faster than TensorFlow 1 code)