{"id":26717965,"url":"https://github.com/erikbavenstrand/neural-network-implementation","last_synced_at":"2026-04-27T21:32:06.324Z","repository":{"id":40975608,"uuid":"222940384","full_name":"ErikBavenstrand/Neural-Network-Implementation","owner":"ErikBavenstrand","description":"An Artificial Neural Network Implementation in Numpy to work with MNIST dataset.","archived":false,"fork":false,"pushed_at":"2024-01-27T15:45:00.000Z","size":11759,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-27T16:41:11.555Z","etag":null,"topics":["ai","feedforward-neural-network","machine-learning","mnist","neural-network","numpy","python"],"latest_commit_sha":null,"homepage":"https://bavenstrand.se","language":"Python","has_issues":false,"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/ErikBavenstrand.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":"2019-11-20T13:10:41.000Z","updated_at":"2023-10-04T13:10:29.000Z","dependencies_parsed_at":"2025-03-27T16:47:06.036Z","dependency_job_id":null,"html_url":"https://github.com/ErikBavenstrand/Neural-Network-Implementation","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ErikBavenstrand/Neural-Network-Implementation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErikBavenstrand%2FNeural-Network-Implementation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErikBavenstrand%2FNeural-Network-Implementation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErikBavenstrand%2FNeural-Network-Implementation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErikBavenstrand%2FNeural-Network-Implementation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ErikBavenstrand","download_url":"https://codeload.github.com/ErikBavenstrand/Neural-Network-Implementation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ErikBavenstrand%2FNeural-Network-Implementation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32356598,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-27T20:07:02.737Z","status":"ssl_error","status_checked_at":"2026-04-27T20:07:00.910Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["ai","feedforward-neural-network","machine-learning","mnist","neural-network","numpy","python"],"created_at":"2025-03-27T16:31:39.860Z","updated_at":"2026-04-27T21:32:06.307Z","avatar_url":"https://github.com/ErikBavenstrand.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Network Implementation with Numpy\n\u003e The project was done for an introductory course in artificial intelligence. The work was done in groups of two.\n\nThe project aimed to implement a simple artificial neural network in Python using Numpy. To then evaluate the implementation, the famous MNIST dataset was used where we achieved a **96%** accuracy. To further investigate the topic, we created our own very small dataset using paint and with that, we achieved a **70%** accuracy. More information about how the neural network was implemented can be found in the project [report](Neural-Network_Report.pdf).\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./images/MNIST.png\" /\u003e\n\u003c/p\u003e\n\n## Usage example\nFirst, you need to install the requirements found in the requirements.txt file. This is preferably done inside a virtual environment.\n```sh\npip install -r requirements.txt\n```\nAfter that, the following command can be run to construct and train a network.\n```sh\npython main.py 784 100 10 NN.bin\n```\n\n## Development setup\n\nPython 3 is required.\n\n\n## Meta\n\nErik Båvenstrand – [Portfolio](https://bavenstrand.se) – erik@bavenstrand.se\n\nDistributed under the MIT license. See ``LICENSE`` for more information.\n\n[github.com/ErikBavenstrand](https://github.com/ErikBavenstrand)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferikbavenstrand%2Fneural-network-implementation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ferikbavenstrand%2Fneural-network-implementation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ferikbavenstrand%2Fneural-network-implementation/lists"}