Character level tokenizers for sequence data

-

A Julia package for real-time audification of ODEs and SDEs

-

-

Data structures for graph neural network

An easy to use Flux implementation of the Kolmogorov Arnold Network. This is a Julia version of TorchKAN.

(Experimental) Predicting hand assignments in piano MIDI using neural networks

Parameter estimation under uncertainty.

PointNeighbors.jl: Neighborhood search with fixed search radius in Julia

Julia package for microstructure imaging

Fast operator-overloading Jacobian & Hessian sparsity detection.

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

Generate checklists and flow diagrams based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)

Compressed belief-state MDPs in Julia compatible with POMDPs.jl

Differentiable tree-based models for tabular data

Simple predictive models for tumor growth, and tools to apply them to clinical data

A small package for differentiable discontinuities in Julia.

Differentiable rasterisation of point clouds in julia

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

Representing machine learning models using mathematical programming

A Julia package for regression in the sphere based on Universal Differential Equations

Ecosystem of numerical methods for microbial kinetics data analysis, from preprocessing to result interpretation.

Julia package for Light Based Tomographic Volumetric Additive Manufacturing.

Differentiable, CUDA supported, image rotation algorithm in Julia.

Layerwise Relevance Propagation in Julia.

Julia Package for Active Inference

GraphNetCore.jl is a software package for the Julia programming language that provides an the core functionality of the MeshGraphNets.jl package. Some parts are based on the implementation of the MeshGraphNets framework by Google DeepMind for simulating mesh-based physical systems via graph neural networks.

MeshGraphNets.jl is a software package for the Julia programming language that provides an implementation of the MeshGraphNets framework by Google DeepMind for simulating mesh-based physical systems via graph neural networks.

Power spectrum inference of irregularly sampled time series using Gaussian Processes in Julia

Optimal experimental design of ODE and DAE systems in julia

Bayesian Safety Signal Detection in Julia

Deep-learning sliding window attention with circular boundary conditions. No tokenization, no patchify-ing.

-

Adds support for parallelization for Taija packages.

-

A decision-making framework for the cost-efficient design of experiments, balancing the value of acquired experimental evidence and incurred costs.

Protein ribbon plots implemented in Julia using Makie

Molecular backbone geometry utilities

-