A remix of Arch Linux ARM for Raspberry Pi 3 B+ built for HackRF and RTL-SDR

PiNN2 is a easy-to-use framework for device compact modeling using physics-inspired neural networks

Downloading and converting OpenWrt image to Raspberry Pi NOOBS/PINN os format

Deep learning library for solving differential equations on top of PyTorch.

A Framework for building custom Physics Informed Neural Networks (PINNs).

A simple, templated script to create PINN-compatible compressed tarballs and metadata from an OS disk image

Physics-informed neural network for solving fluid dynamics problems

Using Physics Informed Neural Networks to solve the Burger's Equation

Develop and implement a PINN to solve the Burguers' Equation. This is the first step in the process of learning how to implement this PINN.

Implementation of a Physics Informed Neural Network (PINN) written in Tensorflow v2, which is capable of solving Partial Differential Equations.

Using cumulative infected cases data from Italy, South Korea, and USA, we simulate mitigation measures including; early detection of infectives, social distancing and contact tracing

Due to the public health intervention and public response, transmission of covid is a nonlinear time-dependent function. using cumulative infected cases data from Italy and USA, we learn time varying transmission rates.

This repo contains the code for solving Poisson Equation using Physics Informed Neural Networks

A standalone project to test libtorch C++ APIs on solving the 2D heat equation with PINN.

PINN (Physics-Informed Neural Networks) on Navier-Stokes Equations

This project is divided in a two parts. In first study, Lame parameters are identified using tanh activation function. After that, six activation functions are analysed on the basis of minimum loss, training time and convergence order for different error norms.

Here I will try to implement the solution of PDEs using PINN on pytorch for educational purpose

This project is a Physics Inspired Neural Network, based on Laplaces equation.

physics-informed neural networks for solving simple differential equations

Using PINN based MPC for motion planning for SDC and LSTM for pedestrain's trajectory prediction as dynamic obstacles