The Dyad Language Kernel

Probably a stupid idea

Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.

Jacobian-Enhanced Neural Networks (JENN) are fully connected multi-layer perceptrons, whose training process was modified to account for gradient information. Specifically, the parameters are learn…

"Full speed or nothing." - James Hetfield

GPU Programming with Julia - course at the Swiss National Supercomputing Centre (CSCS), ETH Zurich

Elegant and Performant Deep Learning

Interactive D3 plots within Pluto!

18.337 - Parallel Computing and Scientific Machine Learning

High-performance automatic differentiation of LLVM and MLIR.

Interface package for featurizing atomic structures

An acausal modeling framework for automatically parallelized scientific machine learning (SciML) in Julia. A computer algebra system for integrated symbolics for physics-informed machine learning a…

Pluto inside a VS Code Webview, WIP

Create container images for using Julia packages (especially useful in environments without Internet access)

Data driven modeling and automated discovery of dynamical systems for the SciML Scientific Machine Learning organization

Parallel Computing and Scientific Machine Learning (SciML): Methods and Applications (MIT 18.337J/6.338J)

Chemical Reaction Neural Network

In progress implementation of using stiff solvers as a means for NNs to update it's weights and learn stiff dynamics

An experimental differentiable diffdrive robot simulator implemented by Pytorch

Reservoir computing utilities for scientific machine learning (SciML)