TinyNS: Platform-Aware Neurosymbolic Auto Tiny Machine Learning

Physics-driven machine learning using PyTorch and Firedrake

Physics-aware machine learning with echo state networks for the prediction of chaotic systems.

This project aims to build a new vision model that reconstructs objects from their in-line holograms. The objective is to minimize the twin-image effects and image artifacts (aberrations, speckles, sensor effects, etc.).

Code for the concept paper presenting physics-aware neural networks for power quality state estimation