Skip to content

Latest commit

 

History

History
executable file
·
233 lines (196 loc) · 23.3 KB

AI.md

File metadata and controls

executable file
·
233 lines (196 loc) · 23.3 KB
Raw

Machine learning and statistics are closely related fields, so do check out the Statistics page for more packages. Category sorting of packages is a WIP.

MACHINE LEARNING

  • BackpropNeuralNet.jl :: A neural network in Julia.
  • BayesianNonparametrics.jl :: Bayesian nonparametrics in Julia.
  • BNMF.jl :: Gamma Process Non-negative Matrix Factorization (GaP-NMF).
  • ConfidenceWeighted.jl :: Confidence weighted, a machine learning algorithm.
  • Contingency.jl :: Assorted techniques for the purpose of enabling automated machine learning.
  • Clustering.jl :: Basic functions for clustering data ==> k-means, dp-means, etc..
  • DAI.jl :: A julia binding to the C++ discrete approximate inference library for graphical models: libDAI.
  • DecisionTree.jl :: Julia implementation of Decision Tree (CART) and Random Forest algorithms.
  • DecisionTrees.jl :: {NotSupported}
  • Discretizers.jl :: A package to support discretization methods and mapping functions for data discretization and label maps.
  • EGR.jl :: The Stochastic Gradient (SG) algorithm for machine learning.
  • ELM.jl :: Extreme Learning Machines are a variant of Single-Hidden Layer Feedforward Networks (SLFNs) with a significant departure as their weights aren't iteratively tuned. This boosts the speed of neurals nets heavily.
  • EmpiricalRiskMinimization.jl :: Empirical Risk Minimization (and modeling) in Julia.
  • FeatureSelection.jl :: Common measures and algorithms for feature selection.
  • Flimsy.jl :: Gradient based Machine Learning for Julia.
  • FunctionalDataUtils.jl :: Utility functions for the FunctionalData package, mainly from the area of computer vision / machine learning.
  • go.jl :: A deep learning based Go bot implemented in Julia.
  • GradientBoost.jl :: Gradient boosting framework for Julia.
  • Glmnet.jl :: Julia wrapper for fitting Lasso/ElasticNet GLM models using glmnet.
  • HopfieldNets.jl :: Discrete and continuous Hopfield networks in Julia.
  • HSIC.jl :: Julia implementations of the Hilbert-Schmidt Independence Criterion (HSIC).
  • JuML.jl :: Machine Learning in Julia.
  • KaggleDigitRecognizer.jl :: Julia code for Kaggle's Digit Recognizer competition.
  • KDTrees.jl :: KD Trees.
  • Keras.jl :: A package built atop Flux to directly load Keras(.py) models into Flux.
  • Kernels.jl :: A Julia package for Mercer kernels and Gramian matrix calculation/approximation functions used in kernel methods of machine learning.
  • Knet.jl :: Koç University deep learning framework - A machine learning module implemented in Julia.
    • KnetNLP :: NLP models and utilities for Knet.
  • kNN.jl :: The k-Nearest Neighbors algorithm in Julia.
  • KSVM.jl by @remusao :: Kernel Support Vector Machine (SVM) written in Julia.
  • KSVM.jl by @Evizero :: Support Vector Machines in pure Julia.
  • Ladder.jl :: A reliable leaderboard algorithm for machine learning competitions.
  • Learn.jl :: Base framework library for machine learning packages.
  • LearnBase.jl :: Abstractions for Julia Machine Learning Packages.
  • LearningStrategies.jl :: A generic and modular framework for building custom iterative algorithms in Julia.
  • liblinear.jl :: Liblinear binding to Julia.
  • LIBSVM.jl :: Julia bindings for LIBSVM.
  • LossFunctions.jl :: Julia package of loss functions for machine learning. Documentation: http://lossesjl.readthedocs.io/
  • NMF.jl :: A Julia package for non-negative matrix factorization (NMF).
  • MachineLearning.jl :: is a Machine Learning library package that consolidates common machine learning algorithms written in pure Julia and presents a consistent API.
  • Merlin.jl :: Flexible Deep Learning Framework in Julia.
  • Mitosis.jl :: Automatic probabilistic programming for scientific machine learning and dynamical models.
  • MLDatasets.jl :: Utility package for accessing common Machine Learning datasets in Julia.
  • MLJ.jl :: MLJ (Machine Learning in Julia) is a toolbox written in Julia providing a common interface and meta-algorithms for selecting, tuning, evaluating, composing and comparing over 160 machine learning models written in Julia and other languages.
  • MLLabelUtils.jl :: Utility package for working with classification targets and label-encodings. Documentation: http://mllabelutilsjl.readthedocs.io/
  • MLKernels.jl :: Mercer kernels and Gramian matrix calculation/approximation.
  • MochaTheano.jl :: Allow use of Theano for automatic differentiation within Mocha, via PyCall.
  • MXNet.jl :: Flexible and efficient deep learning in Julia.
  • NetworkLearning.jl :: Baseline collective classification library.
  • Ollam.jl :: OLLAM = Online Learning of Linear Adaptatable Models.
  • OnlineAI.jl :: Machine learning for sequential/streaming data. {Usable: 3, Robust: 3, Active: 3}
  • Orchestra.jl :: Heterogeneous ensemble learning package for the Julia programming language.
  • ParticleFilters.jl :: Simple particle filter implementation in Julia - works with POMDPs.jl models or others.
  • PredictMD.jl :: Uniform interface for machine learning in Julia.
  • PrivateMultiplicativeWeights.jl :: Differentially private synthetic data.
  • ProjectiveDictionaryPairLearning.jl :: Juia code for the paper S. Gu, L. Zhang, W. Zuo, and X. Feng, “Projective Dictionary Pair Learning for Pattern Classification,” In NIPS 2014.
  • RegERMs.jl :: A package implementing several machine learning algorithms in a regularised empirical risk minimisation framework (SVMs, LogReg, Linear Regression) in Julia.
  • SALSA.jl :: _S_oftware Lab for _A_dvanced Machine _L_earning and _S_tochastic _A_lgorithms is a native Julia implementation of the well known stochastic algorithms for linear and non-linear Support Vector Machines.
  • ScikitLearn.jl :: Julia implementation of the scikit-learn API.
  • ScikitLearnBase.jl :: Definition of the ScikitLearn.jl API.
  • SimpleML.jl :: Textbook implementations of some Machine Learning Algorithms in Julia.
  • SFA.jl :: Implementation of the standard SFA (Slow Feature Analysis) algorithm (both linear and non-linear signal expansion) in Julia.
  • SoftConfidenceWeighted.jl :: Exact Soft Confidence-Weighted Learning.
  • Strada.jl :: A deep learning library for Julia based on Caffe.
  • SVMLightLoader.jl :: Loader of svmlight / liblinear format files.
  • JuliaTakingFittingAPIsSeriously :: proof of concept taking the APIs for statistics, machine learning and other infomatics.
  • TensorFlow.jl :: A Julia wrapper for TensorFlow, the open source machine learning framework from Google.
  • TheDataMustFlow.jl :: Julia tools for feeding tabular data into machine learning.
  • TSVD.jl :: Truncated singular value decomposition with partial reorthogonalization.
  • ValueHistories.jl :: Utilities to efficiently track learning curves or other optimization information.
  • XLATools.jl :: Provides access to XLA and the XRT runtime (in Tensorflow), including the ability to build and compile XLA computations using the IRTools format.
Resources

NLP

English

  • EnglishText.jl :: Utilities for English-language quirks in Julia.
  • Why.jl :: A simple function, why, which gives randomly generated answers.

Finite Automata

Japanese

  • MeCab.jl :: Julia binding of Japanese morphological analyzer MeCab.

REINFORCEMENT LEARNING

  • DeepQLearning.jl :: An implementation of DeepMind's Deep Q Learning algorithm described in Playing Atari with Deep Reinforcement Learning.
  • Flux.jl :: A library for machine learning implemented in Julia. Documentation: https://fluxml.ai/Flux.jl/stable/
    • model-zoo :: A repository containing various demonstrations of the Flux machine learning library that can be freely used as a starting point for your own models.
  • ReinforcementLearning.jl by @jbrea :: A Reinforcement Learning package.
  • ReinforcementLearning.jl by @benhamner :: A Reinforcement Learning package.
  • ReinforcementLearning.jl by @JuliaReinforcementLearning :: A package for reinforcement learning research in Julia.
  • TopoChains.jl :: A flexible data structure for multi-input multi-output model compositions of layers and functions. It provides a new data structure, a TopoChain, which was originally designed as the Stack, as part of Transformers.jl by Peter Cheng, and this has been repackaged here into a standalone package for general purpose use.
  • Transformers.jl :: Julia Implementation of Transformer-based models, with Flux.jl.

SPEECH RECOGNITION

  • JuliaTorch :: Using PyTorch in Julia Language via PyCall.
  • MelGeneralizedCepstrums.jl :: It provides a mel generalized cepstrum analysis for spectrum envelope estimation, which includes linear predicition, mel-cepstrum, generalized cepstrum and mel-generalized cepstrum analysis for Julia.
  • MFCC.jl :: Standard Mel Frequency Cepstral Coefficients feature extraction for speech analysis.
  • SpeechBase.jl.
  • SPTK.jl :: A Julia wrapper for the Speech Signal Processing Toolkit (SPTK), based on the modified version of SPTK.
  • SynthesisFilters.jl :: Speech Synthesis Filters.
  • WORLD.jl :: A Julia wrapper for WORLD - a high-quality speech analysis, modification and synthesis system. WORLD provides a way to decompose a speech signal into: Fundamental frequency (F0), spectral envelope, excitation signal (or aperiodicy used in TANDEM-STRAIGHT), and re-synthesize a speech signal from these paramters. See here for the original WORLD.

SUPERVISED LEARNING

  • GURLS.jl :: A pure Julia port of the GURLS supervised learning library.
  • SupervisedLearning.jl :: Front-end interface for supervised machine learning.
Resources

UNSUPERVISED LEARNING

Neural Networks

  • ANN.jl :: Artifical Neural Networks.
  • Boltzmann.jl :: Restricted Boltzmann Machines and Deep Belief Networks in Julia
  • FANN.jl :: A Julia wrapper for the Fast Artificial Neural Network Library (FANN).
  • hinton.jl :: Create hinton diagrams in Julia. Hinton diagrams are used to visualize weight matrices in neural networks.
  • Julia_Neural_Network :: Basic Neural Network written in JuliaLang.
  • KnetOnnx.jl :: It reads an ONNX file and creates the corresponding Model in Knet that can be re-designed, re-trained or simply used for inference.
  • mlpnnets.jl :: Feed-forward MLP neural network implementation.
  • MultiLabelNeuralNetwork.jl :: A simple feed-forward neural network for multi-label classification.
  • neural.jl :: is a Julia implementation of a neural network, based on Sergio Fierens Ruby version.
  • NeuralNets.jl :: Generic artificial neural networks in Julia.
  • neuralnetwork.jl :: is an implementation of label neural network originally written for MATLAB/Octave by Andrew Ng for Coursera Machine Learning Class.
  • NeuralNetworks.jl :: Various functions for Neural Networks implemented in Julia.
  • ONNX.jl :: Read ONNX graphs and load these models in Julia.
  • PyTorch.jl:: PyTorch wrapper.
  • RecurrentNN.jl :: Deep RNN and LSTM in Julia.
  • RNN.jl :: Recurrent Neural Networks.
  • SimpleNets :: Simple neural nets implementions in Julia.
  • SpikeNet.jl :: A spiking neural network simulator written in Julia.
  • StackedNets.jl :: A simple interface to deep stacks of neural network units that can be trained using gradient descent over defined error measures.
  • SumProductNetworks.jl :: Sum-Product Networks (deep probabilistic networks) package in Julia.
Resources