{"id":31565624,"url":"https://github.com/nlgranger/nnbox","last_synced_at":"2025-10-05T07:13:33.427Z","repository":{"id":92878016,"uuid":"63355800","full_name":"nlgranger/nnbox","owner":"nlgranger","description":"A neural network toolbox for matlab","archived":false,"fork":false,"pushed_at":"2016-07-14T17:22:38.000Z","size":93,"stargazers_count":19,"open_issues_count":0,"forks_count":4,"subscribers_count":6,"default_branch":"master","last_synced_at":"2023-10-20T22:05:52.721Z","etag":null,"topics":["cnn","matconvnet","matlab","neural-network","toolboxes"],"latest_commit_sha":null,"homepage":null,"language":"Matlab","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/nlgranger.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2016-07-14T17:22:02.000Z","updated_at":"2023-10-20T22:05:53.040Z","dependencies_parsed_at":"2023-06-14T13:30:46.465Z","dependency_job_id":null,"html_url":"https://github.com/nlgranger/nnbox","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/nlgranger/nnbox","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlgranger%2Fnnbox","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlgranger%2Fnnbox/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlgranger%2Fnnbox/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlgranger%2Fnnbox/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nlgranger","download_url":"https://codeload.github.com/nlgranger/nnbox/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nlgranger%2Fnnbox/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278421426,"owners_count":25984018,"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","status":"online","status_checked_at":"2025-10-05T02:00:06.059Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cnn","matconvnet","matlab","neural-network","toolboxes"],"created_at":"2025-10-05T07:13:31.942Z","updated_at":"2025-10-05T07:13:33.420Z","avatar_url":"https://github.com/nlgranger.png","language":"Matlab","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NNBox\n\nNNBox is a Matlab \u0026copy; toolbox for neural networks. Many other toolboxes are \nalready available for matlab and may either offer more models, a higher levels \nof support, better optimization, or simply a bigger user community... This \ntoolbox tries to focus on different objectives:\n- Providing very clear and simple implementations of some neural networks \n  models and architectures.\n- Providing a simple template to implement new models rapidly\n- Providing a flexible interface where building blocks can be arranged \n  together easily.\n\nIn particular, this library provides support for Restricted Boltzmann Machines\n(RBM), Convolutional Neural Networks (CNN), simple perceptrons models. It\nallows to arrange these models in parallel, as stacked multiple layers, or even\nin a Siamese network architecture.\n\nThis library does not focus on completeness though, because attempting to do so\nrarely gives satisfying results. Instead it tries to provide simple and\nflexible architectural fundations to help you implement your own model quickly.\n\nFor your information, here is a list of other existing libraries:\n\n- [Matlab Neural Network toolbox](http://fr.mathworks.com/help/nnet/index.html)\n- [DeepLearnToolbox](https://github.com/rasmusbergpalm/DeepLearnToolbox) \n  A popular deep learning toolbox\n- [MEDAL](https://github.com/dustinstansbury/medal) Similarily provides \n  implementations for several sorts of Deep Learning models.\n- [MatConvNet](http://www.vlfeat.org/matconvnet/) Provides awrapper to a C++ \n  implementation of convolutional neural networks. It is actually used here \n  for the CNN model.\n\n\n## Requirements\n\nAs far as I can tell, any version of matlab above R2011a should work, R2014a \nis known to work. Octave is not supported because classes are not yet fully \nsupported.\n\n\n## Installation\n\nJust add nnbox subfolders to your path:\n\n```matlab\naddpath('nnbox/utils:nnbox/networks:nnbox/costfun:nnbox/distances');\n```\n\nCNN implementation requires the [MatConvNet](http://www.vlfeat.org/matconvnet/) \nlibrary as a backend, follow installation instructions and add the matlab \nbindings to the path.\n\n\n## Examples\n\n```matlab\nX = [0  1  0  1;\n     0  0  1  1];\nY = [0 .5 .5  1];\nnet = Perceptron(2, 1, struct('lRate', 0.5));\ntrainOpts = struct('nIter', 100, 'displayEvery', 10);\ntrain(net, SquareCost(), X, Y, trainOpts);\n```\n\n- MNIST figure recognition using a Deep belief network : \n  [examples/MNIST_DNN.m](examples/MNIST_DNN.m)\n\n\n## Documentation\n\nRefer to [DOCUMENTATION.md](DOCUMENTATION.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnlgranger%2Fnnbox","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnlgranger%2Fnnbox","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnlgranger%2Fnnbox/lists"}