{"id":13676418,"url":"https://github.com/jdermody/brightwire","last_synced_at":"2025-04-05T23:07:48.381Z","repository":{"id":40658160,"uuid":"58986200","full_name":"jdermody/brightwire","owner":"jdermody","description":"Bright Wire is an open source machine learning library for .NET with GPU support (via CUDA)","archived":false,"fork":false,"pushed_at":"2024-05-19T22:30:47.000Z","size":48865,"stargazers_count":119,"open_issues_count":6,"forks_count":18,"subscribers_count":24,"default_branch":"master","last_synced_at":"2024-05-28T14:46:37.765Z","etag":null,"topics":["convolutional-neural-networks","csharp","cuda","cuda-support","gpu","gpu-support","machine-learning","machine-learning-library","machinelearning","neural-network","recurrent-neural-networks"],"latest_commit_sha":null,"homepage":"https://github.com/jdermody/brightwire/wiki","language":"C#","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jdermody.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2016-05-17T03:06:21.000Z","updated_at":"2024-05-30T01:01:04.894Z","dependencies_parsed_at":"2024-04-08T23:28:50.127Z","dependency_job_id":"35ae95c5-03c1-4230-8fd6-b6810a0996cb","html_url":"https://github.com/jdermody/brightwire","commit_stats":null,"previous_names":[],"tags_count":24,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jdermody%2Fbrightwire","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jdermody%2Fbrightwire/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jdermody%2Fbrightwire/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jdermody%2Fbrightwire/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jdermody","download_url":"https://codeload.github.com/jdermody/brightwire/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247411234,"owners_count":20934653,"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":["convolutional-neural-networks","csharp","cuda","cuda-support","gpu","gpu-support","machine-learning","machine-learning-library","machinelearning","neural-network","recurrent-neural-networks"],"created_at":"2024-08-02T13:00:26.413Z","updated_at":"2025-04-05T23:07:48.363Z","avatar_url":"https://github.com/jdermody.png","language":"C#","funding_links":[],"categories":["Uncategorized"],"sub_categories":["Uncategorized"],"readme":"![image](https://user-images.githubusercontent.com/1952388/177148366-bb4f2d2f-92af-4f60-a0de-ce5e3b08f135.png)\n\n*Bright Wire* is an extensible machine learning library for .NET with optional MKL and GPU support (via CUDA).\n\n## Getting Started\n\n*Bright Wire* is a .net 8 class library.\n\nThe previous .net 4.6 version can be found here: https://github.com/jdermody/brightwire-v2\n\n*Bright Wire* runs \"out of the box\" with its own vectorised linear algebra library.\n\nIf you have a NVIDIA GPU then you can also use GPU based computation. You will need to install\n[NVIDIA CUDA Toolkit 12](https://developer.nvidia.com/cuda-downloads) \n(and have a [Kepler or better NVIDIA GPU](https://en.wikipedia.org/wiki/CUDA#GPUs_supported)).\n\nTo enable higher performance CPU based computation on Intel hardware, *Bright Wire* also supports the Intel Math Kernel Library (MKL).\n\n## Tutorials\n\n* [Getting Started](https://github.com/jdermody/brightwire/wiki/0.-Getting-Started)\n* [Introduction](https://github.com/jdermody/brightwire/wiki/01.-Introduction)\n* [Classification Overview](https://github.com/jdermody/brightwire/wiki/02.-Classification-Overview)\n* [Building a Simple Language Model](https://github.com/jdermody/brightwire/wiki/03.-Generating-Text-with-Markov-Chains)\n* [Recognising Handwritten Digits (MNIST)](https://github.com/jdermody/brightwire/wiki/04.-Recognising-Handwritten-Digits-(MNIST))\n* [Sentiment Analysis](https://github.com/jdermody/brightwire/wiki/05.-Sentiment-Analysis)\n* [Text Clustering](https://github.com/jdermody/brightwire/wiki/06.-Text-Clustering-Four-Ways)\n* [Simple Recurrent Neural Networks](https://github.com/jdermody/brightwire/wiki/07.-Teaching-a-Recurrent-Neural-Net-Binary-Addition)\n* [GRU Recurrent Neural Networks](https://github.com/jdermody/brightwire/wiki/08.-GRU-Recurrent-Neural-Networks)\n* [Sequence to Sequence Neural Networks with LSTM](https://github.com/jdermody/brightwire/wiki/09.-Sequence-to-Sequence-with-LSTM)\n* [Convolutional Neural Networks](https://github.com/jdermody/brightwire/wiki/10.-Convolutional-Neural-Networks)\n\n## Nuget Installation\n\nTo install the cpu version (no CUDA support) use:\n\n```\nInstall-Package BrightWire\n```\n### MKL\nTo add MKL support use:\n\n```\nInstall-Package BrightWire\nInstall-Package BrightData.MKL\n```\nthen install the MKL.NET nuget installation for your OS, for example `Install-Package MKL.NET.win-x64`\n\n### CUDA\nTo add CUDA support use:\n\n```\nInstall-Package BrightWire\nInstall-Package BrightData.Cuda\n```\n\n## Features\n\n### Neural Networks\n* Feed Forward, Convolutional, Bidirectional and Sequence to Sequence (seq2seq) network architectures\n* LSTM, GRU, Simple, Elman and Jordan recurrent neural networks\n* L2, Dropout and DropConnect regularisation\n* Relu, LeakyRelu, Sigmoid, Tanh and SoftMax activation functions\n* Gaussian, Xavier and Identity weight initialisation\n* Cross Entropy, Quadratic and Binary cost functions\n* Momentum, NesterovMomentum, Adagrad, RMSprop and Adam gradient descent optimisations\n\n### Bayesian\n* Naive Bayes\n* Multinomial Bayes\n* Multivariate Bernoulli\n* Markov Models\n\n### Unsupervised\n* K Means clustering\n* Hierarchical clustering\n* Non Negative Matrix Factorisation\n* Random Projection\n\n### Tree Based\n* Decision Trees\n* Random Forest\n\n### Ensemble Methods\n* Stacking\n\n### Other\n* K Nearest Neighbour classification\n* In-memory and file based data processing\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjdermody%2Fbrightwire","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjdermody%2Fbrightwire","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjdermody%2Fbrightwire/lists"}