Benedict Grey's starred repositories
pytorch_geometric
Graph Neural Network Library for PyTorch
latentpinn
Official repository for the "Multiple wavefield solutions in physics-informed neural networks using latent representation" paper.
WienerLoss
Implementation of an adaptive weiner filter as a loss function for autoencoders and variational autoencoders
discovering_modern_cpp
Source codes of Discovering Modern C++
AE-ConvLSTM-Flow-Dynamics
This repository contains an Auto-encoder ConvLSTM network (Pytorch) which can be used to predict a large number of time steps (100+). The network prediction is sequence-to-sequence which works well to predict 5 to 10-time steps in one pass through the neural network. The network is trained for unsteady fluid simulations using data. Another training method tested is the physics constraint method, where governing equations of fluid motion are used to optimize loss. Few attempts to train unsteady Navier-Stokes are made, but it dint work.
harmonic-oscillator-pinn-workshop
Introductory workshop on PINNs using the harmonic oscillator
hands-on-pinns
A Hands-on Introduction to Physics-Informed Neural Networks
neuraloperator
Learning in infinite dimension with neural operators.
harmonic-oscillator-pinn
Code accompanying my blog post: So, what is a physics-informed neural network?
experiments
Codebase for reproducible benchmarking experiments in MedMNIST v2
introduction-to-python
"Introduction to Python" course for Imperial College London ESE future MSc students