Machine learning, deep learning
Organizations
Resources
- An evaluation of Deep Learning Frameworks
- Caltech’s machine learning course by Prof. Yaser Abu-Mostafa with videos on Youtube.
- Examples from Thoughtful Machine Learning
- Grokking Deep Learning with Julia
- machine-learning-cheat-sheet : Classical equations and diagrams in machine learning by @soulmachine.
- Machine Learning in Julia 2020
- mlpnnets.jl : Feed-forward MLP neural network implementation.
Machine Learning Frameworks
- AutoMLPipeline.jl : a package to create complex ML pipeline structures using simple expressions.
- CombineML.jl : Create ensembles of machine learning models from scikit-learn, caret, and julia.
- EasyML.jl : Using machine learning in Julia through a graphical user interface.
- Lux.jl : A explicitly parameterized neural network using deeply nested named tuples.
- PredictMD.jl : Uniform interface for machine learning in Julia. It is the official machine learning framework of the Brown Center for Biomedical Informatics.
Flux
Flux.jl : Pure Julia ML stack with lightweight abstractions on top of Julia’s native GPU and AD support.
- FastAI.jl : Repository of best practices for deep learning in Julia, inspired by fastai.
- FluxTraining.jl : A powerful, extensible neural net training backend.
- GeometricFlux.jl : Geometric Deep Learning for
Flux.jl. - model-zoo : Various demonstrations of the
Flux.jlmachine learning library.
Knet
Knet.jl : Koç University deep learning framework - A machine learning module implemented in Julia.
- KnetNLP : NLP examples in Knet.
- KnetOnnx.jl : ONNX integration with Knet.
MLJ
MLJ.jl : A Julia machine learning framework by The Alan Turing Institute.
- MLJLinearModels.jl: Generalized Linear Regressions Models for MLJ.
Bindings for external libraries
- LIBLINEAR.jl : Julia binding to Liblinear, a library for Large Linear Classification.
- LIBSVM.jl : Julia bindings for LIBSVM C library.
- ONNX.jl : Read ONNX graphs and load these models in Julia.
- ONNXNaiveNASflux.jl : Import/export ONNX models for
Flux.jl. - ONNXRunTime.jl : Julia bindings for the onnxruntime to perform inference.
- ScikitLearn.jl : Julia implementation of the scikit-learn API via
PyCall.jl. - XGBoost.jl : a Julia interface of XGBoost, an efficient and scalable implementation of distributed gradient boosting framework. Julia Con 2023 Video
Clustering
- Clustering.jl: Basic functions for clustering data e.g, k-means, dp-means, etc..
- DecisionTree.jl : Julia implementation of Decision Tree (CART) and Random Forest algorithms.
- EvoTrees.jl : Boosted decision trees in Julia. JuliaCon 2025
- NearestNeighbors.jl : High performance nearest neighbor data structures and algorithms for Julia.
- UMAP.jl : Uniform Manifold Approximation and Projection (UMAP) implementation in Julia.
Dataset Utilities
- Discretizers.jl : A package to support discretization methods and mapping functions for data discretization and label maps.
- MLDatasets.jl : Utility package for accessing common Machine Learning datasets in Julia.
- MLLabelUtils.jl : Utility package for working with classification targets and label-encodings.
Misc
- Boltzmann.jl : Restricted Boltzmann Machines and Deep Belief Networks in Julia
- ExplainableAI.jl : Explainable AI in Julia.
- InvertibleNetworks.jl : Building blocks for invertible neural networks in the Julia programming language.
- KernelFunctions.jl : Kernel functions for machine learning.
- LossFunctions.jl : Julia package of loss functions for machine learning. Documentation
- NetworkLearning.jl : Baseline collective classification library, including observation-based learning and entity-based learning.
- NeuralVerification.jl : verifying whether a neural network satisfies certain input-output constraints. JuliaCon 2021 video.
- PrivateMultiplicativeWeights.jl : Differentially private synthetic data.
- SimulatedNeuralMoments.jl : Bayesian and classical estimation and inference based on statistics that are filtered through a trained neural net.
- SumProductNetworks.jl : Sum-Product Networks (deep probabilistic networks) package in Julia.
- TopoChains.jl : A flexible data structure for multi-input multi-output models.
- ValueHistories.jl : Utilities to efficiently track learning curves or other optimization information.
Reinforcement Learning (RL)
Wikipedia: Reinforcement Learning
- ReinforcementLearning.jl : A Reinforcement Learning package. Introduction: ReinforcementLearningAnIntroduction.jl
Natural language processing (NLP)
- AdaGram.jl : Adaptive Skip-gram implementation in Julia.
- BKTrees.jl : Julia implementation of Burkhard-Keller trees.
- ConceptnetNumberbatch.jl : Julia interface to ConceptnetNumberbatch.
- CorpusLoaders.jl : A variety of loaders for various NLP corpora.
- DependencyTrees.jl : A package for dependency parsing.
- GloVe.jl : Implements Global Word Vectors.
- Glowe.jl : Julia interface to Global Word Vectors.
- Languages.jl : A package for working with human languages.
- ParserCombinator.jl : A parser combinator library.
- StringAnalysis.jl : A hard fork of the
TextAnalysis.jlpackage, designed to provide a richer, faster and orthogonal API. - TextAnalysis.jl : A Julia package for text analysis.
- TopicModels.jl : Topic models are Bayesian, hierarchical mixture models of discrete data.
- Word2Vec.jl : Julia interface to word2vec.
- WordNet.jl : A Julia package for Princeton’s WordNet®.
English
- EnglishText.jl : Utilities for English-language quirks in Julia.
- Why.jl : A simple function,
why(), which gives randomly generated answers.
Spiking neural network
Wikipedia: Spiking neural network
See also: Neuroscience
- Conductor.jl : a Julia-based neuronal network simulator engine.
- Neuroblox.jl : Multi-scale computational neuroscience models. JuliaCon 2025
- NeuronBuilder.jl : building small networks of detailed, conductance-based neurons out of ion channels and synapses.
- SpikeSynchrony.jl : Measuring distances, synchrony and correlation between spike trains.
- SpikingNeuralNetworks.jl : Julia Spiking Neural Network Simulator.
- WaspNet.jl : fixed-time-step simulations of primarily spiking neural networks (SNNs).