{"id":16487705,"url":"https://github.com/gen1321/yetantotherrubynerualnetwork","last_synced_at":"2026-06-07T18:32:38.833Z","repository":{"id":80353223,"uuid":"95683910","full_name":"gen1321/YetAntotherRubyNerualNetwork","owner":"gen1321","description":null,"archived":false,"fork":false,"pushed_at":"2017-07-01T10:42:21.000Z","size":697,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-01T01:43:44.724Z","etag":null,"topics":["machine-learning","neural-network","ruby"],"latest_commit_sha":null,"homepage":null,"language":"Ruby","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/gen1321.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-06-28T15:24:31.000Z","updated_at":"2024-08-26T20:16:20.000Z","dependencies_parsed_at":"2023-06-06T04:45:13.198Z","dependency_job_id":null,"html_url":"https://github.com/gen1321/YetAntotherRubyNerualNetwork","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/gen1321/YetAntotherRubyNerualNetwork","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gen1321%2FYetAntotherRubyNerualNetwork","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gen1321%2FYetAntotherRubyNerualNetwork/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gen1321%2FYetAntotherRubyNerualNetwork/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gen1321%2FYetAntotherRubyNerualNetwork/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gen1321","download_url":"https://codeload.github.com/gen1321/YetAntotherRubyNerualNetwork/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gen1321%2FYetAntotherRubyNerualNetwork/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34034025,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-07T02:00:07.652Z","response_time":124,"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":["machine-learning","neural-network","ruby"],"created_at":"2024-10-11T13:35:38.897Z","updated_at":"2026-06-07T18:32:38.787Z","avatar_url":"https://github.com/gen1321.png","language":"Ruby","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Yet another Nerual Network With Ruby\n\nHey! this is nerual network is build for educational purposes. It easy to read and understand but it's kinda slow.\n\nThis Neraual network have very simple syntax\n\nFirst of all you need to initialize Network\n\n```\nNet.new([80], 28 * 28, %w[0 1 2 3 4 5 6 7 8 9])\n```\n\nFirst argument is shape of hiden layers. each element of array is represents layer of network. [10] is one layer with 10 neurons, [10, 10] is 2 layer with 10 neurons each\n\nSecond argument is size of input layer. it should be equal to your input size.\n\nThrid argument is shape of output. if we want our network to classify digits we should pass %w[0 1 2 3 4 5 6 7 8 9]. when you call process it will return  something like ['1' =\u003e 0.2, '2' =\u003e 0.8 ..]\n\n```\nprocess([0,0,0,1,2,3,4])\n```\ntakes array of digits that represents your input\nand return hash of `'label' =\u003e probablity`\n\n```\ntrain(array_of_inputs, array_of_expected_results)\n```\nexample `train([[0,0,0,1,2,3,4], [0,0,0,2,2,3,3]], [[0,1], [1,0]])`\n\n\n## MNIST\n\nin example folder you can find HelloWorld of Neraual Networks, OCR on handwriten digits with MNIST dataset.\n\nwith this implementation i managed to get around 60-70% of success. Dont forget to put dataset to examples folder\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgen1321%2Fyetantotherrubynerualnetwork","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgen1321%2Fyetantotherrubynerualnetwork","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgen1321%2Fyetantotherrubynerualnetwork/lists"}