{"id":13749821,"url":"https://github.com/alexsosn/iOS_ML","last_synced_at":"2025-05-09T13:30:45.439Z","repository":{"id":36654620,"uuid":"40960931","full_name":"alexsosn/iOS_ML","owner":"alexsosn","description":"List of Machine Learning, AI, NLP solutions for iOS. The most recent version of this article can be found on my blog.","archived":false,"fork":false,"pushed_at":"2018-07-30T19:55:52.000Z","size":98,"stargazers_count":1433,"open_issues_count":2,"forks_count":154,"subscribers_count":93,"default_branch":"master","last_synced_at":"2025-05-06T03:01:49.338Z","etag":null,"topics":["artificial-intelligence","awesome-list","computer-vision","deep-learning","gpgpu","machine-learning","natural-language-processing","neural-network","speech-recognition","swift"],"latest_commit_sha":null,"homepage":"https://alexsosn.github.io/ml/2015/11/05/iOS-ML.html","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alexsosn.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2015-08-18T08:44:46.000Z","updated_at":"2025-04-18T08:44:51.000Z","dependencies_parsed_at":"2022-09-12T10:20:58.558Z","dependency_job_id":null,"html_url":"https://github.com/alexsosn/iOS_ML","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexsosn%2FiOS_ML","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexsosn%2FiOS_ML/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexsosn%2FiOS_ML/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alexsosn%2FiOS_ML/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alexsosn","download_url":"https://codeload.github.com/alexsosn/iOS_ML/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253258120,"owners_count":21879591,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["artificial-intelligence","awesome-list","computer-vision","deep-learning","gpgpu","machine-learning","natural-language-processing","neural-network","speech-recognition","swift"],"created_at":"2024-08-03T07:01:13.743Z","updated_at":"2025-05-09T13:30:45.160Z","avatar_url":"https://github.com/alexsosn.png","language":null,"funding_links":[],"categories":["Others","Other Lists","swift"],"sub_categories":["TeX Lists"],"readme":"# Machine Learning for iOS \n\n**Last Update: January 12, 2018.**\n\nCurated list of resources for iOS developers in following topics: \n\n- [Core ML](#coreml)\n- [Machine Learning Libraries](#gpmll)\n- [Deep Learning Libraries](#dll)\n    - [Deep Learning: Model Compression](#dlmc)\n- [Computer Vision](#cv)\n- [Natural Language Processing](#nlp)\n- [Speech Recognition (TTS) and Generation (STT)](#tts)\n- [Text Recognition (OCR)](#ocr)\n- [Other AI](#ai)\n- [Machine Learning Web APIs](#web)\n- [Opensource ML Applications](#mlapps)\n- [Game AI](#gameai)\n- Other related staff\n    - [Linear algebra](#la)\n    - [Statistics, random numbers](#stat)\n    - [Mathematical optimization](#mo)\n    - [Feature extraction](#fe)\n    - [Data Visualization](#dv)\n    - [Bioinformatics (kinda)](#bio)\n    - [Big Data (not really)](#bd)\n- [iOS ML Blogs](#blogs)\n- [Mobile ML books](#books)\n- [GPU Computing Blogs](#gpublogs)\n- [Learn Machine Learning](#learn)\n- [Other Lists](#lists)\n\nMost of the de-facto standard tools in AI-related domains are written in iOS-unfriendly languages (Python/Java/R/Matlab) so finding something appropriate for your iOS application may be a challenging task.\n\nThis list consists mainly of libraries written in Objective-C, Swift, C, C++, JavaScript and some other languages that can be easily ported to iOS. Also, I included links to some relevant web APIs, blog posts, videos and learning materials.\n\nResources are sorted alphabetically or randomly. The order doesn't reflect my personal preferences or anything else. Some of the resources are awesome, some are great, some are fun, and some can serve as an inspiration.\n\nHave fun!\n\n**Pull-requests are welcome [here](https://github.com/alexsosn/iOS_ML)**.\n\n# \u003ca name=\"coreml\"/\u003eCore ML\n\n* [coremltools](https://pypi.python.org/pypi/coremltools) is a Python package. It contains converters from some popular machine learning libraries to the Apple format.\n* [Core ML](https://developer.apple.com/documentation/coreml) is an Apple framework to run inference on device. It is highly optimized to Apple hardware.\n\nCurrently CoreML is compatible (partially) with the following machine learning packages via [coremltools python package](https://apple.github.io/coremltools/):\n\n- [Caffe](http://caffe.berkeleyvision.org)\n- [Keras](https://keras.io/)\n- [libSVM](https://www.csie.ntu.edu.tw/~cjlin/libsvm/)\n- [scikit-learn](http://scikit-learn.org/)\n- [XGBoost](https://xgboost.readthedocs.io/en/latest/)\n\nThird-party converters to [CoreML format](https://apple.github.io/coremltools/coremlspecification/) are also available for some models from:\n\n- [Turicreate](https://github.com/apple/turicreate)\n- [TensorFlow](https://github.com/tf-coreml/tf-coreml)\n- [MXNet](https://github.com/apache/incubator-mxnet/tree/master/tools/coreml)\n- [Torch7](https://github.com/prisma-ai/torch2coreml)\n- [CatBoost](https://tech.yandex.com/catboost/doc/dg/features/export-model-to-core-ml-docpage/)\n\nThere are many curated lists of pre-trained neural networks in Core ML format: [\\[1\\]](https://github.com/SwiftBrain/awesome-CoreML-models), [\\[2\\]](https://github.com/cocoa-ai/ModelZoo), [\\[3\\]](https://github.com/likedan/Awesome-CoreML-Models).\n\nCore ML currently doesn't support training models, but still, you can replace model by downloading a new one from a server in runtime. [Here is a demo](https://github.com/zedge/DynamicCoreML) of how to do it. It uses generator part of MNIST GAN as Core ML model.\n\n# \u003ca name=\"gpmll\"/\u003eGeneral-Purpose Machine Learning Libraries\n\u003cp\u003e\u003c/p\u003e\n\u003ctable rules=\"groups\"\u003e\n\u003cthead\u003e \n  \u003ctr\u003e\n    \u003cth style=\"text-align: center\"\u003eLibrary\u003c/th\u003e\n    \u003cth style=\"text-align: center\"\u003eAlgorithms\u003c/th\u003e \n    \u003cth style=\"text-align: center\"\u003eLanguage\u003c/th\u003e \n    \u003cth style=\"text-align: center\"\u003eLicense\u003c/th\u003e\n    \u003cth style=\"text-align: center\"\u003eCode\u003c/th\u003e\n    \u003cth style=\"text-align: center\"\u003eDependency manager\u003c/th\u003e\n  \u003c/tr\u003e\n\u003c/thead\u003e \n    \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/KevinCoble/AIToolbox\"\u003eAIToolbox\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n\u003cul\u003e\n\u003cli\u003eGraphs/Trees\u003c/li\u003e\n\u003cul\u003e\n    \u003cli\u003eDepth-first search\u003c/li\u003e\n    \u003cli\u003eBreadth-first search\u003c/li\u003e\n    \u003cli\u003eHill-climb search\u003c/li\u003e\n    \u003cli\u003eBeam Search\u003c/li\u003e\n    \u003cli\u003eOptimal Path search\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli\u003eAlpha-Beta (game tree)\u003c/li\u003e\n\u003cli\u003eGenetic Algorithms\u003c/li\u003e\n\u003cli\u003eConstraint Propogation\u003c/li\u003e\n\u003cli\u003eLinear Regression\u003c/li\u003e\n\u003cli\u003eNon-Linear Regression\u003c/li\u003e\n\u003cul\u003e\n    \u003cli\u003eparameter-delta\u003c/li\u003e\n    \u003cli\u003eGradient-Descent\u003c/li\u003e\n    \u003cli\u003eGauss-Newton\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli\u003eLogistic Regression\u003c/li\u003e\n\u003cli\u003eNeural Networks\u003c/li\u003e\n\u003cul\u003e\n    \u003cli\u003emultiple layers, several non-linearity models\u003c/li\u003e\n    \u003cli\u003eon-line and batch training\u003c/li\u003e\n    \u003cli\u003efeed-forward or simple recurrent layers can be mixed in one network\u003c/li\u003e\n    \u003cli\u003eLSTM network layer implemented - needs more testing\u003c/li\u003e\n    \u003cli\u003egradient check routines\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli\u003eSupport Vector Machine\u003c/li\u003e\n\u003cli\u003eK-Means\u003c/li\u003e\n\u003cli\u003ePrincipal Component Analysis\u003c/li\u003e\n\u003cli\u003eMarkov Decision Process\u003c/li\u003e\n\u003cul\u003e\n    \u003cli\u003eMonte-Carlo (every-visit, and first-visit)\u003c/li\u003e\n    \u003cli\u003eSARSA\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli\u003eSingle and Multivariate Gaussians\u003c/li\u003e\n\u003cli\u003eMixture Of Gaussians\u003c/li\u003e\n\u003cli\u003eModel validation\u003c/li\u003e\n\u003cli\u003eDeep Network\u003c/li\u003e\n\u003cul\u003e\n    \u003cli\u003eConvolution layers\u003c/li\u003e\n    \u003cli\u003ePooling layers\u003c/li\u003e\n    \u003cli\u003eFully-connected NN layers\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/ul\u003e\n\u003c/td\u003e \n    \u003ctd\u003eSwift\u003c/td\u003e \n    \u003ctd\u003eApache 2.0\u003c/td\u003e\n    \u003ctd\u003e\u003cp\u003e\u003ca href=\"https://github.com/KevinCoble/AIToolbox\"\u003eGitHub\u003c/a\u003e\u003c/p\u003e\u003c/td\u003e\n    \u003ctd\u003e \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\n        \u003ca href=\"http://dlib.net/\"\u003e\n            \u003cimg src=\"http://dlib.net/dlib-logo.png\" width=\"100\" \u003e\n        \u003cbr\u003edlib\u003c/a\u003e\n    \u003c/td\u003e\n        \u003ctd\u003e\n            \u003cul\u003e\n            \u003cli\u003eDeep Learning\u003c/li\u003e\n            \u003cli\u003eSupport Vector Machines\u003c/li\u003e\n            \u003cli\u003eReduced-rank methods for large-scale classification and regression\u003c/li\u003e\n            \u003cli\u003eRelevance vector machines for classification and regression\u003c/li\u003e\n            \u003cli\u003eA Multiclass SVM\u003c/li\u003e\n            \u003cli\u003eStructural SVM\u003c/li\u003e\n            \u003cli\u003eA large-scale SVM-Rank\u003c/li\u003e\n            \u003cli\u003eAn online kernel RLS regression\u003c/li\u003e\n            \u003cli\u003eAn online SVM classification algorithm\u003c/li\u003e\n            \u003cli\u003eSemidefinite Metric Learning\u003c/li\u003e\n            \u003cli\u003eAn online kernelized centroid estimator/novelty detector and offline support vector one-class classification\u003c/li\u003e\n            \u003cli\u003eClustering algorithms: linear or kernel k-means, Chinese Whispers, and Newman clustering\u003c/li\u003e\n            \u003cli\u003eRadial Basis Function Networks\u003c/li\u003e\n            \u003cli\u003eMulti layer perceptrons\u003c/li\u003e\n            \u003c/ul\u003e\n    \u003c/td\u003e \n    \u003ctd\u003eC++\u003c/td\u003e \n    \u003ctd\u003eBoost\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/davisking/dlib\"\u003eGitHub\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"http://leenissen.dk/fann/wp/\"\u003eFANN\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n        \u003cul\u003e\n\u003cli\u003eMultilayer Artificial Neural Network\u003c/li\u003e\n\u003cli\u003eBackpropagation (RPROP, Quickprop, Batch, Incremental)\u003c/li\u003e\n\u003cli\u003eEvolving topology training\u003c/li\u003e\n\u003c/ul\u003e\n\u003c/td\u003e \n    \u003ctd\u003eC++\u003c/td\u003e \n    \u003ctd\u003eGNU LGPL 2.1\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/libfann/fann\"\u003eGitHub\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://cocoapods.org/pods/FANN\"\u003eCocoa Pods\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/lemire/lbimproved\"\u003elbimproved\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003ek-nearest neighbors and Dynamic Time Warping\u003c/td\u003e \n    \u003ctd\u003eC++\u003c/td\u003e \n    \u003ctd\u003eApache 2.0\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/lemire/lbimproved\"\u003eGitHub\u003c/a\u003e \u003c/td\u003e\n    \u003ctd\u003e \u003c/td\u003e\n  \u003c/tr\u003e\n    \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/gianlucabertani/MAChineLearning\"\u003eMAChineLearning\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n    \u003cul\u003e\n    \u003cli\u003eNeural Networks\u003c/li\u003e\n    \u003cul\u003e\n    \u003cli\u003eActivation functions: Linear, ReLU, Step, sigmoid, TanH\u003c/li\u003e\n    \u003cli\u003eCost functions: Squared error, Cross entropy\u003c/li\u003e\n    \u003cli\u003eBackpropagation: Standard, Resilient (a.k.a. RPROP).\u003c/li\u003e\n    \u003cli\u003eTraining by sample or by batch.\u003c/li\u003e\n    \u003c/ul\u003e\n    \u003cli\u003eBag of Words\u003c/li\u003e\n    \u003cli\u003eWord Vectors\u003c/li\u003e\n\u003c/ul\u003e\n    \u003c/td\u003e \n    \u003ctd\u003eObjective-C\u003c/td\u003e \n    \u003ctd\u003eBSD 3-clause\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/gianlucabertani/MAChineLearning\"\u003eGitHub\u003c/a\u003e \u003c/td\u003e\n    \u003ctd\u003e \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/Somnibyte/MLKit\"\u003e\u003cimg width=\"100\" src=\"https://github.com/Somnibyte/MLKit/raw/master/MLKitSmallerLogo.png\"\u003e\u003cbr\u003eMLKit\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e \n    \u003cul\u003e\n    \u003cli\u003eLinear Regression: simple, ridge, polynomial\u003c/li\u003e\n    \u003cli\u003eMulti-Layer Perceptron, \u0026 Adaline ANN Architectures\u003c/li\u003e\n    \u003cli\u003eK-Means Clustering\u003c/li\u003e\n    \u003cli\u003eGenetic Algorithms\u003c/li\u003e\n    \u003c/ul\u003e\n\u003c/td\u003e \n    \u003ctd\u003eSwift\u003c/td\u003e\n    \u003ctd\u003eMIT\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/Somnibyte/MLKit\"\u003eGitHub\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://cocoapods.org/pods/MachineLearningKit\"\u003eCocoa Pods\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/saniul/Mendel\"\u003e\u003cimg width=\"100\" src=\"https://github.com/saniul/Mendel/raw/master/logo@2x.png\"\u003e\u003cbr\u003eMendel\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003eEvolutionary/genetic algorithms\u003c/td\u003e \n    \u003ctd\u003eSwift\u003c/td\u003e \n    \u003ctd\u003e?\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/saniul/Mendel\"\u003eGitHub\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/vincentherrmann/multilinear-math\"\u003emultilinear-math\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n        \u003cul\u003e\n    \u003cli\u003eLinear algebra and tensors\u003c/li\u003e\n    \u003cli\u003ePrincipal component analysis\u003c/li\u003e\n    \u003cli\u003eMultilinear subspace learning algorithms for dimensionality reduction\u003c/li\u003e\n    \u003cli\u003eLinear and logistic regression\u003c/li\u003e\n    \u003cli\u003eStochastic gradient descent\u003c/li\u003e\n    \u003cli\u003eFeedforward neural networks\u003c/li\u003e\n    \u003cul\u003e\n    \u003cli\u003eSigmoid\u003c/li\u003e\n    \u003cli\u003eReLU\u003c/li\u003e\n    \u003cli\u003eSoftplus activation functions\u003c/li\u003e\n    \u003c/ul\u003e\n    \u003c/ul\u003e\n    \u003c/td\u003e \n    \u003ctd\u003eSwift\u003c/td\u003e \n    \u003ctd\u003eApache 2.0\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/vincentherrmann/multilinear-math\"\u003eGitHub\u003c/a\u003e \u003c/td\u003e\n    \u003ctd\u003eSwift Package Manager\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"http://opencv.org/\"\u003e\u003cimg width=\"100\" src=\"http://opencv.org/assets/theme/logo.png\"\u003eOpenCV\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n    \u003cul\u003e\n    \u003cli\u003eMulti-Layer Perceptrons\u003c/li\u003e \n    \u003cli\u003eBoosted tree classifier\u003c/li\u003e \n    \u003cli\u003edecision tree\u003c/li\u003e \n    \u003cli\u003eExpectation Maximization\u003c/li\u003e \n    \u003cli\u003eK-Nearest Neighbors\u003c/li\u003e \n    \u003cli\u003eLogistic Regression\u003c/li\u003e \n    \u003cli\u003eBayes classifier\u003c/li\u003e \n    \u003cli\u003eRandom forest\u003c/li\u003e \n    \u003cli\u003eSupport Vector Machines\u003c/li\u003e  \n    \u003cli\u003eStochastic Gradient Descent SVM classifier\u003c/li\u003e \n    \u003cli\u003eGrid search\u003c/li\u003e \n    \u003cli\u003eHierarchical k-means\u003c/li\u003e \n    \u003cli\u003eDeep neural networks\u003c/li\u003e\n    \u003c/ul\u003e\n    \u003c/td\u003e \n    \u003ctd\u003eC++\u003c/td\u003e \n    \u003ctd\u003e3-clause BSD\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/opencv\"\u003eGitHub\u003c/a\u003e \u003c/td\u003e\n    \u003ctd\u003e \u003ca href=\"https://cocoapods.org/pods/OpenCV\"\u003eCocoa Pods\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"http://image.diku.dk/shark/sphinx_pages/build/html/index.html\"\u003e\u003cimg width=\"100\" src=\"http://image.diku.dk/shark/sphinx_pages/build/html/_static/SharkLogo.png\"\u003e\u003cbr\u003eShark\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n    \u003cul\u003e\n    \u003cli\u003e\u003cb\u003eSupervised:\u003c/b\u003e \u003c/li\u003e\n    \u003cul\u003e\n    \u003cli\u003eLinear discriminant analysis (LDA)\u003c/li\u003e\n    \u003cli\u003eFisher–LDA\u003c/li\u003e\n    \u003cli\u003eLinear regression\u003c/li\u003e\n    \u003cli\u003eSVMs\u003c/li\u003e\n    \u003cli\u003eFF NN\u003c/li\u003e\n    \u003cli\u003eRNN\u003c/li\u003e\n    \u003cli\u003eRadial basis function networks\u003c/li\u003e\n    \u003cli\u003eRegularization networks\u003c/li\u003e\n    \u003cli\u003eGaussian processes for regression\u003c/li\u003e\n    \u003cli\u003eIterative nearest neighbor classification and regression\u003c/li\u003e\n    \u003cli\u003eDecision trees\u003c/li\u003e\n    \u003cli\u003eRandom forest\u003c/li\u003e\n    \u003c/ul\u003e\n    \u003cli\u003e\u003cb\u003eUnsupervised:\u003c/b\u003e \u003c/li\u003e\n    \u003cul\u003e\n    \u003cli\u003ePCA\u003c/li\u003e\n    \u003cli\u003eRestricted Boltzmann machines\u003c/li\u003e\n    \u003cli\u003eHierarchical clustering\u003c/li\u003e\n    \u003cli\u003eData structures for efficient distance-based clustering\u003c/li\u003e\n\u003c/ul\u003e\n    \u003cli\u003e\u003cb\u003eOptimization:\u003c/b\u003e \u003c/li\u003e\n    \u003cul\u003e\n    \u003cli\u003eEvolutionary algorithms\u003c/li\u003e \n    \u003cli\u003eSingle-objective optimization (e.g., CMA–ES)\u003c/li\u003e\n    \u003cli\u003eMulti-objective optimization\u003c/li\u003e\n    \u003cli\u003eBasic linear algebra and optimization algorithms\u003c/li\u003e\n    \u003c/ul\u003e \n\u003c/ul\u003e\n    \u003c/td\u003e \n    \u003ctd\u003eC++\u003c/td\u003e \n    \u003ctd\u003eGNU LGPL\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/lemire/lbimproved\"\u003eGitHub\u003c/a\u003e \u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://cocoapods.org/pods/Shark-SDK\"\u003eCocoa Pods\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/yconst/YCML\"\u003e\u003cimg width=\"100\" src=\"https://raw.githubusercontent.com/yconst/YCML/master/Logo.png\"\u003e\u003cbr\u003eYCML\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n    \u003cul\u003e\n    \u003cli\u003eGradient Descent Backpropagation\u003c/li\u003e \n    \u003cli\u003eResilient Backpropagation (RProp)\u003c/li\u003e \n    \u003cli\u003eExtreme Learning Machines (ELM)\u003c/li\u003e \n    \u003cli\u003eForward Selection using Orthogonal Least Squares (for RBF Net), also with the PRESS statistic\u003c/li\u003e \n    \u003cli\u003eBinary Restricted Boltzmann Machines (CD \u0026 PCD)\u003c/li\u003e\n    \u003cli\u003e\u003cb\u003eOptimization algorithms\u003c/b\u003e: \u003c/li\u003e\n    \u003cul\u003e\n    \u003cli\u003eGradient Descent (Single-Objective, Unconstrained)\u003c/li\u003e \n    \u003cli\u003eRProp Gradient Descent (Single-Objective, Unconstrained)\u003c/li\u003e \n    \u003cli\u003eNSGA-II (Multi-Objective, Constrained)\u003c/li\u003e\n    \u003c/ul\u003e\n    \u003c/ul\u003e\n    \u003c/td\u003e \n    \u003ctd\u003eObjective-C\u003c/td\u003e \n    \u003ctd\u003eGNU GPL 3.0\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/yconst/ycml/\"\u003eGitHub\u003c/a\u003e \u003c/td\u003e\n    \u003ctd\u003e \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd style=\"text-align: center\"\u003e\u003ca href=\"https://github.com/Kalvar\"\u003e\u003cimg width=\"100\" src=\"https://avatars2.githubusercontent.com/u/1835631?v=4\u0026s=460\"\u003e\u003cbr\u003eKalvar Lin's libraries\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\n    \u003cul\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRHebbian-Algorithm\"\u003eios-KRHebbian-Algorithm\u003c/a\u003e - \u003ca href=\"https://en.wikipedia.org/wiki/Hebbian_theory\"\u003eHebbian Theory\u003c/a\u003e\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRKmeans-Algorithm\"\u003eios-KRKmeans-Algorithm\u003c/a\u003e - \u003ca href=\"https://en.wikipedia.org/wiki/K-means_clustering\"\u003eK-Means\u003c/a\u003e clustering method.\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRFuzzyCMeans-Algorithm\"\u003eios-KRFuzzyCMeans-Algorithm\u003c/a\u003e - \u003ca href=\"https://en.wikipedia.org/wiki/Fuzzy_clustering\"\u003eFuzzy C-Means\u003c/a\u003e, the fuzzy clustering algorithm.\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRGreyTheory\"\u003eios-KRGreyTheory\u003c/a\u003e - \u003ca href=\"http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.678.3477\u0026amp;rep=rep1\u0026amp;type=pdf\"\u003eGrey Theory\u003c/a\u003e / \u003ca href=\"http://www.mecha.ee.boun.edu.tr/Prof.%20Dr.%20Okyay%20Kaynak%20Publications/c%20Journal%20Papers(appearing%20in%20SCI%20or%20SCIE%20or%20CompuMath)/62.pdf\"\u003eGrey system theory-based models in time series prediction\u003c/a\u003e\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRSVM\"\u003eios-KRSVM\u003c/a\u003e - Support Vector Machine and SMO.\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRKNN\"\u003eios-KRKNN\u003c/a\u003e - kNN implementation.\u003c/li\u003e\n    \u003cli\u003e\u003ca href=\"https://github.com/Kalvar/ios-KRRBFNN\"\u003eios-KRRBFNN\u003c/a\u003e - Radial basis function neural network and OLS.\u003c/li\u003e\n    \u003c/ul\u003e \n    \u003c/td\u003e \n    \u003ctd\u003eObjective-C\u003c/td\u003e \n    \u003ctd\u003eMIT\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"https://github.com/Kalvar\"\u003eGitHub\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\n**Multilayer perceptron implementations:**\n\n- [Brain.js](https://github.com/harthur/brain) - JS\n- [SNNeuralNet](https://github.com/devongovett/SNNeuralNet) - Objective-C port of brain.js\n- [MLPNeuralNet](https://github.com/nikolaypavlov/MLPNeuralNet) - Objective-C, Accelerate\n- [Swift-AI](https://github.com/Swift-AI/Swift-AI) - Swift\n- [SwiftSimpleNeuralNetwork](https://github.com/davecom/SwiftSimpleNeuralNetwork) - Swift\n- \u003ca href=\"https://github.com/Kalvar/ios-BPN-NeuralNetwork\"\u003eios-BPN-NeuralNetwork\u003c/a\u003e - Objective-C\n- \u003ca href=\"https://github.com/Kalvar/ios-Multi-Perceptron-NeuralNetwork\"\u003eios-Multi-Perceptron-NeuralNetwork\u003c/a\u003e- Objective-C\n- \u003ca href=\"https://github.com/Kalvar/ios-KRDelta\"\u003eios-KRDelta\u003c/a\u003e - Objective-C\n- [ios-KRPerceptron](https://github.com/Kalvar/ios-KRPerceptron) - Objective-C\n\n# \u003ca name=\"dll\"/\u003eDeep Learning Libraries: \n\n### On-Device training and inference\n\n* [Birdbrain](https://github.com/jordenhill/Birdbrain) - RNNs and FF NNs on top of Metal and Accelerate. Not ready for production.\n* [BrainCore](https://github.com/aleph7/BrainCore) - simple but fast neural network framework written in Swift. It uses Metal framework to be as fast as possible. ReLU, LSTM, L2 ...\n* [Caffe](http://caffe.berkeleyvision.org) - A deep learning framework developed with cleanliness, readability, and speed in mind. [GitHub](https://github.com/BVLC/caffe). [BSD]\n    * [iOS port](https://github.com/aleph7/caffe)\n    * [caffe-mobile](https://github.com/solrex/caffe-mobile) - another iOS port.\n    * C++ examples: [Classifying ImageNet](http://caffe.berkeleyvision.org/gathered/examples/cpp_classification.html), [Extracting Features](http://caffe.berkeleyvision.org/gathered/examples/feature_extraction.html)\n    * [Caffe iOS sample](https://github.com/noradaiko/caffe-ios-sample)\n* [Caffe2](https://caffe2.ai/) - a cross-platform framework made with expression, speed, and modularity in mind.\n    * [Cocoa Pod](https://github.com/RobertBiehl/caffe2-ios) \n    * [iOS demo app](https://github.com/KleinYuan/Caffe2-iOS)\n* [Convnet.js](http://cs.stanford.edu/people/karpathy/convnetjs/) - ConvNetJS is a Javascript library for training Deep Learning models by [Andrej Karpathy](https://twitter.com/karpathy). [GitHub](https://github.com/karpathy/convnetjs)\n    * [ConvNetSwift](https://github.com/alexsosn/ConvNetSwift) - Swift port [work in progress].\n* [Deep Belief SDK](https://github.com/jetpacapp/DeepBeliefSDK) -  The SDK for Jetpac's iOS Deep Belief image recognition framework\n* [TensorFlow](http://www.tensorflow.org/) - an open source software library for numerical computation using data flow graphs. Nodes in the graph represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.\n    * [iOS examples](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/ios_examples)\n    * [another example](https://github.com/hollance/TensorFlow-iOS-Example)\n    * [Perfect-TensorFlow](https://github.com/PerfectlySoft/Perfect-TensorFlow) - TensorFlow binding for [Perfect](http://perfect.org/) (server-side Swift framework). Includes only C TF API.\n* [tiny-dnn](https://github.com/tiny-dnn/tiny-dnn) - header only, dependency-free deep learning framework in C++11.\n    * [iOS example](https://github.com/tiny-dnn/tiny-dnn/tree/d4fff53fa0d01f59eb162de2ec32c652a1f6f467/examples/ios) \n* [Torch](http://torch.ch/) is a scientific computing framework with wide support for machine learning algorithms.\n    * [Torch4iOS](https://github.com/jhondge/torch4ios)\n    * [Torch-iOS](https://github.com/clementfarabet/torch-ios)\n\n### Deep Learning: Running pre-trained models on device\n\nThese libraries doesn't support training, so you need to pre-train models in some ML framework.\n\n* [Bender](https://github.com/xmartlabs/Bender) - Framework for building fast NNs. Supports TensorFlow models. It uses Metal under the hood.\n* [Core ML](#coreml)\n* [DeepLearningKit](http://deeplearningkit.org/) - Open Source Deep Learning Framework from Memkite for Apple's tvOS, iOS and OS X.\n* [Espresso](https://github.com/codinfox/espresso) - A minimal high performance parallel neural network framework running on iOS.\n* [Forge](https://github.com/hollance/Forge) - A neural network toolkit for Metal.\n* [Keras.js](https://transcranial.github.io/keras-js/#/) - run [Keras](https://keras.io/) models in a web view. \n* [KSJNeuralNetwork](https://github.com/woffle/KSJNeuralNetwork) - A Neural Network Inference Library Built atop BNNS and MPS\n    * [Converter for Torch models](https://github.com/woffle/torch2ios)\n* [MXNet](https://mxnet.incubator.apache.org/) - MXNet is a deep learning framework designed for both efficiency and flexibility.\n    * [Deploying pre-trained mxnet model to a smartphone](https://mxnet.incubator.apache.org/how_to/smart_device.html)\n* [Quantized-CNN](https://github.com/jiaxiang-wu/quantized-cnn) - compressed convolutional neural networks for Mobile Devices\n* [WebDNN](https://mil-tokyo.github.io/webdnn/) - You can run deep learning model in a web view if you want. Three modes: WebGPU acceleration, WebAssembly acceleration and pure JS (on CPU). No training, inference only.\n\n### Deep Learning: Low-level routines libraries\n\n* [BNNS](https://developer.apple.com/reference/accelerate/1912851-bnns) - Apple Basic neural network subroutines (BNNS) is a collection of functions that you use to implement and run neural networks, using previously obtained training data.\n    * [BNNS usage examples](https://github.com/shu223/iOS-10-Sampler) in iOS 10 sampler.\n    * [An example](https://github.com/bignerdranch/bnns-cocoa-example) of a neural network trained by tensorflow and executed using BNNS\n* [MetalPerformanceShaders](https://developer.apple.com/reference/metalperformanceshaders) - CNNs on GPU from Apple.\n    * [MetalCNNWeights](https://github.com/kakugawa/MetalCNNWeights) - a Python script to convert Inception v3 for MPS.\n    * [MPSCNNfeeder](https://github.com/kazoo-kmt/MPSCNNfeeder) - Keras to MPS models conversion.\n* [NNPACK](https://github.com/Maratyszcza/NNPACK) - Acceleration package for neural networks on multi-core CPUs. Prisma [uses](http://prisma-ai.com/libraries.html) this library in the mobile app.\n* [STEM](https://github.com/abeschneider/stem) - Swift Tensor Engine for Machine-learning\n    * [Documentation](http://stem.readthedocs.io/en/latest/) \n\n### \u003ca name=\"dlmc\"/\u003eDeep Learning: Model Compression\n\n* TensorFlow implementation of [knowledge distilling](https://github.com/chengshengchan/model_compression) method\n* [MobileNet-Caffe](https://github.com/shicai/MobileNet-Caffe) - Caffe Implementation of Google's MobileNets\n* [keras-surgeon](https://github.com/BenWhetton/keras-surgeon) - Pruning for trained Keras models.\n\n\n# \u003ca name=\"cv\"/\u003eComputer Vision\n\n\n* [ccv](http://libccv.org) - C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library\n    * [iOS demo app](https://github.com/liuliu/klaus)\n* [OpenCV](http://opencv.org) – Open Source Computer Vision Library. [BSD]\n    * [OpenCV crash course](http://www.pyimagesearch.com/free-opencv-crash-course/) \n    * [OpenCVSwiftStitch](https://github.com/foundry/OpenCVSwiftStitch)\n    * [Tutorial: using and building openCV on iOS devices](http://maniacdev.com/2011/07/tutorial-using-and-building-opencv-open-computer-vision-on-ios-devices)\n    * [A Collection of OpenCV Samples For iOS](https://github.com/woffle/OpenCV-iOS-Demos)\n* [OpenFace](https://github.com/TadasBaltrusaitis/OpenFace) – a state-of-the art open source tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.\n    * [iOS port](https://github.com/FaceAR/OpenFaceIOS)\n    * [iOS demo](https://github.com/FaceAR/OpenFaceIOS)\n* [trackingjs](http://trackingjs.com/) – Object tracking in JS\n* [Vision](https://developer.apple.com/documentation/vision) is an Apple framework for computer vision.\n\n# \u003ca name=\"nlp\"/\u003eNatural Language Processing\n\n\n* [CoreLinguistics](https://github.com/rxwei/CoreLinguistics) - POS tagging (HMM), ngrams, Naive Bayes, IBM alignment models.\n* [GloVe](https://github.com/rxwei/GloVe-swift) Swift package. Vector words representations.\n* [NSLinguisticTagger](http://nshipster.com/nslinguistictagger/)\n* [Parsimmon](https://github.com/ayanonagon/Parsimmon)\n* [Twitter text](https://github.com/twitter/twitter-text-objc) - \nAn Objective-C implementation of Twitter's text processing library. The library includes methods for extracting user names, mentions headers, hashtags, and more – all the tweet specific language syntax you could ever want.\n* [Verbal expressions for Swift](https://github.com/VerbalExpressions/SwiftVerbalExpressions), like regexps for humans.\n* [Word2Vec](https://code.google.com/p/word2vec/) - Original C implementation of Word2Vec Deep Learning algorithm. Works on iPhone like a charm.\n\n# \u003ca name=\"tts\"/\u003eSpeech Recognition (TTS) and Generation (STT)\n\n\n* [Kaldi-iOS framework](http://keenresearch.com/) - on-device speech recognition using deep learning.\n    * [Proof of concept app](https://github.com/keenresearch/kaldi-ios-poc)\n* [MVSpeechSynthesizer](https://github.com/vimalmurugan89/MVSpeechSynthesizer)\n* [OpenEars™: free speech recognition and speech synthesis for the iPhone](http://www.politepix.com/openears/) - OpenEars™ makes it simple for you to add offline speech recognition and synthesized speech/TTS to your iPhone app quickly and easily. It lets everyone get the great results of using advanced speech UI concepts like statistical language models and finite state grammars in their app, but with no more effort than creating an NSArray or NSDictionary. \n    * [Tutorial (Russian)](http://habrahabr.ru/post/237589/)\n* [TLSphinx](https://github.com/tryolabs/TLSphinx), [Tutorial](http://blog.tryolabs.com/2015/06/15/tlsphinx-automatic-speech-recognition-asr-in-swift/)\n\n# \u003ca name=\"ocr\"/\u003eText Recognition (OCR)\n\n\n* [ocrad.js](https://github.com/antimatter15/ocrad.js) - JS OCR\n* **Tesseract**\n    * [Install and Use Tesseract on iOS](http://lois.di-qual.net/blog/install-and-use-tesseract-on-ios-with-tesseract-ios/)\n    * [tesseract-ios-lib](https://github.com/ldiqual/tesseract-ios-lib)\n    * [tesseract-ios](https://github.com/ldiqual/tesseract-ios)\n    * [Tesseract-OCR-iOS](https://github.com/gali8/Tesseract-OCR-iOS)\n    * [OCR-iOS-Example](https://github.com/robmathews/OCR-iOS-Example)\n\n# \u003ca name=\"ai\"/\u003eOther AI\n\n\n* [Axiomatic](https://github.com/JadenGeller/Axiomatic) - Swift unification framework for logic programming.\n* [Build Your Own Lisp In Swift](https://github.com/hollance/BuildYourOwnLispInSwift)\n* [Logician](https://github.com/mdiep/Logician) - Logic programming in Swift\n* [Swiftlog](https://github.com/JadenGeller/Swiftlog) - A simple Prolog-like language implemented entirely in Swift.\n\n# \u003ca name=\"web\"/\u003eMachine Learning Web APIs\n\n\n* [**IBM** Watson](http://www.ibm.com/smarterplanet/us/en/ibmwatson/developercloud/) - Enable Cognitive Computing Features In Your App Using IBM Watson's Language, Vision, Speech and Data APIs.\n    * [Introducing the (beta) IBM Watson iOS SDK](https://developer.ibm.com/swift/2015/12/18/introducing-the-new-watson-sdk-for-ios-beta/)\n* [AlchemyAPI](http://www.alchemyapi.com/) - Semantic Text Analysis APIs Using Natural Language Processing. Now part of IBM Watson.\n* [**Microsoft** Project Oxford](https://www.projectoxford.ai/)\n* [**Google** Prediction engine](https://cloud.google.com/prediction/docs)\n    * [Objective-C API](https://code.google.com/p/google-api-objectivec-client/wiki/Introduction)\n* [Google Translate API](https://cloud.google.com/translate/docs)\n* [Google Cloud Vision API](https://cloud.google.com/vision/)\n* [**Amazon** Machine Learning](http://aws.amazon.com/documentation/machine-learning/) - Amazon ML is a cloud-based service for developers. It provides visualization tools to create machine learning models. Obtain predictions for application using APIs. \n    * [iOS developer guide](https://docs.aws.amazon.com/mobile/sdkforios/developerguide/getting-started-machine-learning.html).\n    * [iOS SDK](https://github.com/aws/aws-sdk-ios)\n* [**PredictionIO**](https://prediction.io/) - opensource machine learning server for developers and ML engineers. Built on Apache Spark, HBase and Spray.\n    * [Swift SDK](https://github.com/minhtule/PredictionIO-Swift-SDK)\n    * [Tapster iOS Demo](https://github.com/minhtule/Tapster-iOS-Demo) - This demo demonstrates how to use the PredictionIO Swift SDK to integrate an iOS app with a PredictionIO engine to make your mobile app more interesting.\n    * [Tutorial](https://github.com/minhtule/Tapster-iOS-Demo/blob/master/TUTORIAL.md) on using Swift with PredictionIO.\n* [**Wit.AI**](https://wit.ai/) - NLP API\n* [**Yandex** SpeechKit](https://tech.yandex.com/speechkit/mobilesdk/) Text-to-speech and speech-to-text for Russian language. iOS SDK available.\n* [**Abbyy** OCR SDK](http://www.abbyy.com/mobile-ocr/iphone-ocr/)\n* [**Clarifai**](http://www.clarifai.com/#) - deep learning web api for image captioning. [iOS starter project](https://github.com/Clarifai/clarifai-ios-starter)\n* [**MetaMind**](https://www.metamind.io/) - deep learning web api for image captioning.\n* [Api.AI](https://api.ai/) - Build intelligent speech interfaces\nfor apps, devices, and web\n* [**CloudSight.ai**](https://cloudsight.ai/) - deep learning web API for fine grained object detection or whole screen description, including natural language object captions. [Objective-C](https://github.com/cloudsight/cloudsight-objc) API client is available.\n\n# \u003ca name=\"mlapps\"/\u003eOpensource ML Applications\n\n\n### Deep Learning\n\n* [DeepDreamer](https://github.com/johndpope/deepdreamer) - Deep Dream application\n* [DeepDreamApp](https://github.com/johndpope/DeepDreamApp) - Deep Dream Cordova app.\n* [Texture Networks](https://github.com/DmitryUlyanov/texture_nets), Lua implementation\n* [Feedforward style transfer](https://github.com/jcjohnson/fast-neural-style), Lua implementation\n* [TensorFlow implementation of Neural Style](https://github.com/cysmith/neural-style-tf)\n* [Corrosion detection app](https://github.com/jmolayem/corrosionapp)\n* [ios_camera_object_detection](https://github.com/yjmade/ios_camera_object_detection) - Realtime mobile visualize based Object Detection based on TensorFlow and YOLO model\n* [TensorFlow MNIST iOS demo](https://github.com/mattrajca/MNIST) - Getting Started with Deep MNIST and TensorFlow on iOS\n* [Drummer App](https://github.com/hollance/RNN-Drummer-Swift) with RNN and Swift\n* [What'sThis](https://github.com/pppoe/WhatsThis-iOS)\n* [enVision](https://github.com/IDLabs-Gate/enVision) - Deep Learning Models for Vision Tasks on iOS\\\n* [GoogLeNet on iOS demo](https://github.com/krasin/MetalDetector)\n* [Neural style in Android](https://github.com/naman14/Arcade)\n* [mnist-bnns](https://github.com/paiv/mnist-bnns) - TensorFlow MNIST demo port to BNNS\n* [Benchmark of BNNS vs. MPS](https://github.com/hollance/BNNS-vs-MPSCNN)\n* [VGGNet on Metal](https://github.com/hollance/VGGNet-Metal)\n* A [Sudoku Solver](https://github.com/waitingcheung/deep-sudoku-solver) that leverages TensorFlow and iOS BNNS for deep learning.\n* [HED CoreML Implementation](https://github.com/s1ddok/HED-CoreML) is a demo with tutorial on how to use Holistically-Nested Edge Detection on iOS with CoreML and Swift\n\n### Traditional Computer Vision\n\n* [SwiftOCR](https://github.com/garnele007/SwiftOCR)\n* [GrabCutIOS](https://github.com/naver/grabcutios) - Image segmentation using GrabCut algorithm for iOS\n\n### NLP\n\n* [Classical ELIZA chatbot in Swift](https://gist.github.com/hollance/be70d0d7952066cb3160d36f33e5636f)\n* [InfiniteMonkeys](https://github.com/craigomac/InfiniteMonkeys) - A Keras-trained RNN to emulate the works of a famous poet, powered by BrainCore\n\n### Other\n\n* [Swift implementation of Joel Grus's \"Data Science from Scratch\"](https://github.com/graceavery/LearningMachineLearning)\n* [Neural Network built in Apple Playground using Swift](https://github.com/Luubra/EmojiIntelligence)\n\n# \u003ca name=\"gameai\"/\u003eGame AI\n\n\n* [Introduction to AI Programming for Games](http://www.raywenderlich.com/24824/introduction-to-ai-programming-for-games)\n* [dlib](http://dlib.net/) is a library which has many useful tools including machine learning.\n* [MicroPather](http://www.grinninglizard.com/MicroPather/) is a path finder and A* solver (astar or a-star) written in platform independent C++ that can be easily integrated into existing code.\n* Here is a [list](http://www.ogre3d.org/tikiwiki/List+Of+Libraries#Artificial_intelligence) of some AI libraries suggested on OGRE3D website. Seems they are mostly written in C++.\n* [GameplayKit Programming Guide](https://developer.apple.com/library/content/documentation/General/Conceptual/GameplayKit_Guide/)\n\n# Other related staff\n\n### \u003ca name=\"la\"/\u003eLinear algebra\n\n\n* [Accelerate-in-Swift](https://github.com/hyperjeff/Accelerate-in-Swift) - Swift example codes for the Accelerate.framework\n* [cuda-swift](https://github.com/rxwei/cuda-swift) - Swift binding to CUDA. Not iOS, but still interesting.\n* [Dimensional](https://github.com/JadenGeller/Dimensional) - Swift matrices with friendly semantics and a familiar interface.\n* [Eigen](http://eigen.tuxfamily.org/) - A high-level C++ library of template headers for linear algebra, matrix and vector operations, numerical solvers and related algorithms. [MPL2]\n* [Matrix](https://github.com/hollance/Matrix) - convenient matrix type with different types of subscripts, custom operators and predefined matrices. A fork of Surge.\n* [NDArray](https://github.com/t-ae/ndarray) - Float library for Swift, accelerated with Accelerate Framework.\n* [Swift-MathEagle](https://github.com/rugheid/Swift-MathEagle) - A general math framework to make using math easy. Currently supports function solving and optimisation, matrix and vector algebra, complex numbers, big int, big frac, big rational, graphs and general handy extensions and functions.\n* [SwiftNum](https://github.com/donald-pinckney/SwiftNum) - linear algebra, fft, gradient descent, conjugate GD, plotting.\n* [Swix](https://github.com/scottsievert/swix) - Swift implementation of NumPy and OpenCV wrapper.\n* [Surge](https://github.com/mattt/Surge) from Mattt\n* [Upsurge](https://github.com/aleph7/Upsurge) - generic tensors, matrices on top of Accelerate. A fork of Surge.\n* [YCMatrix](https://github.com/yconst/YCMatrix) - A flexible Matrix library for Objective-C and Swift (OS X / iOS)\n\n### \u003ca name=\"stat\"/\u003eStatistics, random numbers\n\n\n* [SigmaSwiftStatistics](https://github.com/evgenyneu/SigmaSwiftStatistics) - A collection of functions for statistical calculation written in Swift.\n* [SORandom](https://github.com/SebastianOsinski/SORandom) - Collection of functions for generating psuedorandom variables from various distributions\n* [RandKit](https://github.com/aidangomez/RandKit) - Swift framework for random numbers \u0026 distributions.\n\n\n### \u003ca name=\"mo\"/\u003eMathematical optimization\n\n\n* [fmincg-c](https://github.com/gautambhatrcb/fmincg-c) - Conjugate gradient implementation in C\n* [libLBFGS](https://github.com/chokkan/liblbfgs) - a C library of Limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS)\n* [SwiftOptimizer](https://github.com/haginile/SwiftOptimizer) - QuantLib Swift port.\n\n### \u003ca name=\"fe\"/\u003eFeature extraction\n\n\n* [IntuneFeatures](https://github.com/venturemedia/intune-features) framework contains code to generate features from audio files and feature labels from the respective MIDI files.\n* [matchbox](https://github.com/hfink/matchbox) - Mel-Frequency-Cepstral-Coefficients and Dynamic-Time-Warping for iOS/OSX. **Warning: the library was updated last time when iOS 4 was still hot.**\n* [LibXtract](https://github.com/jamiebullock/LibXtract) is a simple, portable, lightweight library of audio feature extraction functions.\n\n### \u003ca name=\"dv\"/\u003eData Visualization\n\n\n* [Charts](https://github.com/danielgindi/Charts) - The Swift port of the MPAndroidChart.\n* [iOS-Charts](https://github.com/danielgindi/ios-charts)\n* [Core Plot](https://github.com/core-plot/core-plot)\n* [Awesome iOS charts](https://github.com/sxyx2008/awesome-ios-chart)\n* [JTChartView](https://github.com/kubatru/JTChartView)\n* [VTK](http://www.vtk.org/gallery/)\n    * [VTK in action](http://www.vtk.org/vtk-in-action/)\n* [D3.js iOS binding](https://github.com/lee-leonardo/iOS-D3) \n\n### \u003ca name=\"bio\"/\u003eBioinformatics (kinda)\n\n\n* [BioJS](http://biojs.net/) - a set of tools for bioinformatics in the browser. BioJS builds a infrastructure, guidelines and tools to avoid the reinvention of the wheel in life sciences. Community builds modules than can be reused by anyone.\n* [BioCocoa](http://www.bioinformatics.org/biococoa/wiki/pmwiki.php) - BioCocoa is an open source OpenStep (GNUstep/Cocoa) framework for bioinformatics written in Objective-C. [Dead project].\n* [iBio](https://github.com/Lizhen0909/iBio) - A Bioinformatics App for iPhone.\n\n### \u003ca name=\"bd\"/\u003eBig Data (not really)\n\n\n* [HDF5Kit](https://github.com/aleph7/HDF5Kit) - This is a Swift wrapper for the HDF5 file format. HDF5 is used in the scientific comunity for managing large volumes of data. The objective is to make it easy to read and write HDF5 files from Swift, including playgrounds.\n\n### \u003ca name=\"ip\"/\u003eIPython + Swift\n\n\n* [iSwift](https://github.com/KelvinJin/iSwift) - Swift kernel for IPython notebook.\n\n# \u003ca name=\"blogs\"/\u003eiOS ML Blogs\n\n\n### Regular mobile ML\n\n* **[The \"Machine, think!\" blog](http://machinethink.net/blog/) by Matthijs Hollemans**\n    * [The “hello world” of neural networks](http://matthijshollemans.com/2016/08/24/neural-network-hello-world/) - Swift and BNNS\n    * [Convolutional neural networks on the iPhone with VGGNet](http://matthijshollemans.com/2016/08/30/vggnet-convolutional-neural-network-iphone/)\n* **[Pete Warden's blog](https://petewarden.com/)**\n    * [How to Quantize Neural Networks with TensorFlow](https://petewarden.com/2016/05/03/how-to-quantize-neural-networks-with-tensorflow/)\n\n### Accidental mobile ML\n\n* **[Google research blog](https://research.googleblog.com)**\n* **[Apple Machine Learning Journal](https://machinelearning.apple.com/)**\n* **[Invasive Code](https://www.invasivecode.com/weblog/) blog**\n    * [Machine Learning for iOS](https://www.invasivecode.com/weblog/machine-learning-swift-ios/)\n    * [Convolutional Neural Networks in iOS 10 and macOS](https://www.invasivecode.com/weblog/convolutional-neural-networks-ios-10-macos-sierra/)\n* **Big Nerd Ranch** - [Use TensorFlow and BNNS to Add Machine Learning to your Mac or iOS App](https://www.bignerdranch.com/blog/use-tensorflow-and-bnns-to-add-machine-learning-to-your-mac-or-ios-app/)\n\n### Other\n\n* [Intelligence in Mobile Applications](https://medium.com/@sadmansamee/intelligence-in-mobile-applications-ca3be3c0e773#.lgk2gt6ik)\n* [An exclusive inside look at how artificial intelligence and machine learning work at Apple](https://backchannel.com/an-exclusive-look-at-how-ai-and-machine-learning-work-at-apple-8dbfb131932b)\n* [Presentation on squeezing DNNs for mobile](https://www.slideshare.net/mobile/anirudhkoul/squeezing-deep-learning-into-mobile-phones)\n* [Curated list of papers on deep learning models compression and acceleration](https://handong1587.github.io/deep_learning/2015/10/09/acceleration-model-compression.html)\n\n# \u003ca name=\"gpublogs\"/\u003eGPU Computing Blogs\n\n\n* [OpenCL for iOS](https://github.com/linusyang/opencl-test-ios) - just a test.\n* Exploring GPGPU on iOS. \n    * [Article](http://ciechanowski.me/blog/2014/01/05/exploring_gpgpu_on_ios/) \n    * [Code](https://github.com/Ciechan/Exploring-GPGPU-on-iOS)\n\n* GPU-accelerated video processing for Mac and iOS. [Article](http://www.sunsetlakesoftware.com/2010/10/22/gpu-accelerated-video-processing-mac-and-ios0).\n\n* [Concurrency and OpenGL ES](https://developer.apple.com/library/ios/documentation/3ddrawing/conceptual/opengles_programmingguide/ConcurrencyandOpenGLES/ConcurrencyandOpenGLES.html) - Apple programming guide.\n\n* [OpenCV on iOS GPU usage](http://stackoverflow.com/questions/10704916/opencv-on-ios-gpu-usage) - SO discussion.\n\n### Metal\n\n* Simon's Gladman \\(aka flexmonkey\\) [blog](http://flexmonkey.blogspot.com/)\n    * [Talk on iOS GPU programming](https://realm.io/news/altconf-simon-gladman-ios-gpu-programming-with-swift-metal/) with Swift and Metal at Realm Altconf.\n    * [The Supercomputer In Your Pocket:\nMetal \u0026 Swift](https://realm.io/news/swift-summit-simon-gladman-metal/) - a video from the Swift Summit Conference 2015\n    * https://github.com/FlexMonkey/MetalReactionDiffusion\n    * https://github.com/FlexMonkey/ParticleLab\n* [Memkite blog](http://memkite.com/) - startup intended to create deep learning library for iOS.\n    * [Swift and Metal example for General Purpose GPU Processing on Apple TVOS 9.0](https://github.com/memkite/MetalForTVOS)\n    * [Data Parallel Processing with Swift and Metal on GPU for iOS8](https://github.com/memkite/SwiftMetalGPUParallelProcessing)\n    * [Example of Sharing Memory between GPU and CPU with Swift and Metal for iOS8](http://memkite.com/blog/2014/12/30/example-of-sharing-memory-between-gpu-and-cpu-with-swift-and-metal-for-ios8/)\n* [Metal by Example blog](http://metalbyexample.com/)\n* [objc-io article on Metal](https://www.objc.io/issues/18-games/metal/)\n\n# \u003ca name=\"books\"/\u003eMobile ML Books\n\n* \u003cb\u003eBuilding Mobile Applications with TensorFlow\u003c/b\u003e by Pete Warden. [Book page](http://www.oreilly.com/data/free/building-mobile-applications-with-tensorflow.csp). \u003cb\u003e[Free download](http://www.oreilly.com/data/free/building-mobile-applications-with-tensorflow.csp?download=true)\u003c/b\u003e\n\n# \u003ca name=\"learn\"/\u003eLearn Machine Learning\n\n\u003ci\u003ePlease note that in this section, I'm not trying to collect another list of ALL machine learning study resources, but only composing a list of things that I found useful.\u003c/i\u003e\n\n* \u003cb\u003e[Academic Torrents](http://academictorrents.com/browse.php?cat=7)\u003c/b\u003e. Sometimes awesome courses or datasets got deleted from their sites. But this doesn't mean, that they are lost.\n* [Arxiv Sanity Preserver](http://www.arxiv-sanity.com/) - a tool to keep pace with the ML research progress.\n\n## Free Books\n\n* Immersive Linear Algebra [interactive book](http://immersivemath.com/ila/index.html) by J. Ström, K. Åström, and T. Akenine-Möller.\n* [\"Natural Language Processing with Python\"](http://www.nltk.org/book/) - free online book.\n* [Probabilistic Programming \u0026 Bayesian Methods for Hackers](http://camdavidsonpilon.github.io/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/) - An intro to Bayesian methods and probabilistic programming from a computation/understanding-first, mathematics-second point of view. \n* [\"Deep learning\"](http://www.deeplearningbook.org/) - the book by Ian Goodfellow and Yoshua Bengio and Aaron Courville\n\n## Free Courses\n\n* [Original Machine Learning Coursera course](https://www.coursera.org/learn/machine-learning/home/info) by Andrew Ng.\n* [Machine learning playlist on Youtube](https://www.youtube.com/playlist?list=PLD0F06AA0D2E8FFBA).\n* Free online interactive book [\"Neural Networks and Deep Learning\"](http://neuralnetworksanddeeplearning.com/).\n* [Heterogeneous Parallel Programming](https://www.coursera.org/course/hetero) course.\n* [Deep Learning for Perception](https://computing.ece.vt.edu/~f15ece6504/) by Virginia Tech, Electrical and Computer Engineering, Fall 2015: ECE 6504\n* [CAP 5415 - Computer Vision](http://crcv.ucf.edu/courses/CAP5415/Fall2014/index.php) by UCF\n* [CS224d: Deep Learning for Natural Language Processing](http://cs224d.stanford.edu/syllabus.html) by Stanford\n* [Machine Learning: 2014-2015 Course materials](https://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/) by Oxford\n* [Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition.](http://cs231n.stanford.edu/)\n* [Deep Learning for Natural Language Processing \\(without Magic\\)](http://nlp.stanford.edu/courses/NAACL2013/)\n* [Videos](http://videolectures.net/deeplearning2015_montreal/) from Deep Learning Summer School, Montreal 2015.\n* [Deep Learning Summer School, Montreal 2016](http://videolectures.net/deeplearning2016_montreal/)\n\n\n# \u003ca name=\"lists\"/\u003eOther Lists\n\n\n* [Awesome Machine Learning](https://github.com/josephmisiti/awesome-machine-learning)\n* [Machine Learning Courses](https://github.com/prakhar1989/awesome-courses#machine-learning)\n* [Awesome Data Science](https://github.com/okulbilisim/awesome-datascience)\n* [Awesome Computer Vision](https://github.com/jbhuang0604/awesome-computer-vision)\n* [Speech and language processing](https://github.com/edobashira/speech-language-processing)\n* [The Rise of Chat Bots:](https://stanfy.com/blog/the-rise-of-chat-bots-useful-links-articles-libraries-and-platforms/)  Useful Links, Articles, Libraries and Platforms by Pavlo Bashmakov.\n* [Awesome Machine Learning for Cyber Security](https://github.com/jivoi/awesome-ml-for-cybersecurity)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexsosn%2FiOS_ML","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falexsosn%2FiOS_ML","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falexsosn%2FiOS_ML/lists"}