{"id":17861637,"url":"https://github.com/marcusbuffett/three.js-neural-network-visualizer","last_synced_at":"2025-07-03T21:39:57.772Z","repository":{"id":82055975,"uuid":"42958921","full_name":"marcusbuffett/Three.js-Neural-Network-Visualizer","owner":"marcusbuffett","description":"A neural network visualizer using Three.js that recognizes 3s","archived":false,"fork":false,"pushed_at":"2018-04-04T03:52:32.000Z","size":764,"stargazers_count":31,"open_issues_count":1,"forks_count":8,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-05-01T13:08:28.755Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"JavaScript","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/marcusbuffett.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":"2015-09-22T20:25:54.000Z","updated_at":"2023-08-01T13:45:37.000Z","dependencies_parsed_at":null,"dependency_job_id":"5902def0-9893-4a0f-a2af-8085010af404","html_url":"https://github.com/marcusbuffett/Three.js-Neural-Network-Visualizer","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/marcusbuffett/Three.js-Neural-Network-Visualizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcusbuffett%2FThree.js-Neural-Network-Visualizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcusbuffett%2FThree.js-Neural-Network-Visualizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcusbuffett%2FThree.js-Neural-Network-Visualizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcusbuffett%2FThree.js-Neural-Network-Visualizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/marcusbuffett","download_url":"https://codeload.github.com/marcusbuffett/Three.js-Neural-Network-Visualizer/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/marcusbuffett%2FThree.js-Neural-Network-Visualizer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263409466,"owners_count":23462264,"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":[],"created_at":"2024-10-28T08:46:42.627Z","updated_at":"2025-07-03T21:39:57.419Z","avatar_url":"https://github.com/marcusbuffett.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Three.js-Neural-Network-Visualizer\nA neural network visualizer using Three.js that recognizes 3s\n\nCheck it out here : http://marcusbuffett.github.io/Three.js-Neural-Network-Visualizer/\n\n##The Data\n\nThe input is a column vector of 25 numbers (aka a 1D array of 25 numbers), and the output is a one dimensional vector (aka an array with a single number in it). \n\nThe test data looks like this (`1`s highlighted for clarity) : \n\n![Test Data](http://i.imgur.com/o9j06Hd.png)\n\n##The Results\n\nHere's an example of a neural network trained for 90 iterations, with a learning rate of 0.5 and one hidden layer with two neurons.\n\n![Trained network](http://i.imgur.com/LQZF9MY.png)\n\nThe blue lines represent positive weights, the orange lines represent negative weights, and the size of the neurons represent the average absolute weight that the nodes it's connected to assign it's output (roughly translated, the neuron's importance to the network).\n\nSensor and output neurons are represented by cubes, and hidden layers are represented by spheres.\n\n## Running\n\nInstall required stuff:\n```sh\nnpm install -g bower\nbower install\nnpm install\n```\n\nCompile coffeescript:\n```sh\nbrowserify -t coffeeify --extension=\".coffee\" coffee/main.coffee \u003e scripts/main.js\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarcusbuffett%2Fthree.js-neural-network-visualizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmarcusbuffett%2Fthree.js-neural-network-visualizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmarcusbuffett%2Fthree.js-neural-network-visualizer/lists"}