-

Fast accurate creation, detection and analysis of quantum vortex distributions.

A differentiable parametrization of a group of unitary matrices.

Deep Unfolded Convolutional Dictionary Learning for motif discovery.

Generic UNet implementation written in pure Julia, based on Flux.jl

A turbulence-convection single column model cloud parameterization.

Neural network training, fast and easy.

External Machine Learning Libs for TSML

A package for time series data processing, classification, clustering, and prediction.

A small Julia package to facilitate working with the Trillion Dollar Words dataset.

TreeParzen.jl, a pure Julia hyperparameter optimiser with MLJ integration

Julia Implementation of Transformer models

Simple, blazing fast, transformer components.

Makie visualization module for TopOpt.jl

A package for binary and continuous, single and multi-material, truss and continuum, 2D and 3D topology optimization on unstructured meshes using automatic differentiation in Julia.

-

A pure Julia implementation of the Targeted Minimum Loss-based Estimation

Neural Network based models for Natural Language Processing

A text classification library using the microtc approach

A Julia wrapper for TensorFlow

A package for plotting custom symbols from Taija packages.

Adds support for parallelization for Taija packages.

-

Base package that ships symbols and functionality that is relevant to all or multiple packages in the ecosystem

SymbolicNumericIntegration.jl: Symbolic-Numerics for Solving Integrals

Bosons/Fermions Superfluid problem with morden tools.

Subspace Inference package for uncertainty analysis in deep neural networks and neural ordinary differential equations using Julia

-

A Julia package for building production-ready measures (metrics) for statistics and machine learning

Measures (metrics) for statistics and machine learning

Structural Similarity Index Measure loss function for use with AD systems in Julia

Play atmospheric modelling like it's LEGO.

A Julia implementation of sparse Gaussian processes via path-wise doubly stochastic variational inference.

Useful sparse codes

SossMLJ makes it easy to build MLJ machines from user-defined models from the Soss probabilistic programming language

Lightweight module for fusing physical and neural models

SMLMBoxer.jl is a Julia package that provides a fast and efficient method for detecting particles or blobs in a multidimensional image stack and cutting out sub-regions around local maxima.

-

A high-performance library for gradient based quantum optimal control

Interpretable Machine Learning via Rule Extraction