{"id":21057774,"url":"https://github.com/magnushelliesen/neural-network","last_synced_at":"2026-04-15T14:38:29.633Z","repository":{"id":208113589,"uuid":"720771392","full_name":"magnushelliesen/neural-network","owner":"magnushelliesen","description":"Homemade neural network-class with a train/backpropagation method.","archived":false,"fork":false,"pushed_at":"2025-03-08T09:01:16.000Z","size":90157,"stargazers_count":0,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-08T09:32:18.527Z","etag":null,"topics":["artificial-neural-networks","backpropagation","linear-algebra","machine-learning","neural-networks","object-oriented-programming","stochastic-gradient-descent","unit-testing"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/magnushelliesen.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":"2023-11-19T14:55:54.000Z","updated_at":"2025-03-08T09:01:20.000Z","dependencies_parsed_at":"2025-03-08T09:38:47.319Z","dependency_job_id":null,"html_url":"https://github.com/magnushelliesen/neural-network","commit_stats":null,"previous_names":["magnushelliesen/neural-network"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/magnushelliesen%2Fneural-network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/magnushelliesen%2Fneural-network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/magnushelliesen%2Fneural-network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/magnushelliesen%2Fneural-network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/magnushelliesen","download_url":"https://codeload.github.com/magnushelliesen/neural-network/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243502386,"owners_count":20301041,"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":["artificial-neural-networks","backpropagation","linear-algebra","machine-learning","neural-networks","object-oriented-programming","stochastic-gradient-descent","unit-testing"],"created_at":"2024-11-19T17:04:39.190Z","updated_at":"2026-04-15T14:38:29.622Z","avatar_url":"https://github.com/magnushelliesen.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# neural-network\nI've built a [neural network-class](https://github.com/magnushelliesen/neural-network/blob/main/neural_network/neural_network.py) (from first principles, i.e., calculus and linear algebra only, using NumPy) with a train/backpropagation method and everything.\n\nThe class can be installed using\n```python\npip install git+https://github.com/magnushelliesen/neural-network.git\n```\n\nThe class seems to be able to train on the [MNIST dataset](https://git-disl.github.io/GTDLBench/datasets/mnist_datasets/) (see [notebook](https://github.com/magnushelliesen/neural-network/blob/main/notebooks/demo-neural-network-mnist-test.ipynb)), it recognizes most (but not all) handwritten digits. Look how effortlessly it recognizes even this squiggly \"9\":\n\n![image](https://github.com/magnushelliesen/neural-network/assets/104299371/11f036eb-f39b-4ffb-b413-398532a93f72)\n\nIt was a lot of tinkering to get it flying, lemme tell ya! What did the trick was to switch from batch gradient descent to stochastic gradient descent (and removing som bugs/errors). This is really cool!\n\nI'm considering renaming this project/class \"SonOfAnton\" (for those who get the reference).\n\n![image](https://github.com/magnushelliesen/neural-network/assets/104299371/3aa8d57c-5754-4687-9aef-9b5b6b603ab7)\n\n## Testing\nThis repo is set up with two GitHub Actions to make sure I don't merge code that breaks stuff into main:\n1. A [GitHub Action](https://github.com/magnushelliesen/neural-network/blob/main/.github/workflows/run-tests.yml) that runs unit tests on the class upon PR into main\n2. A [GitHub Action](https://github.com/magnushelliesen/neural-network/blob/main/.github/workflows/pre-commit-checks.yml) that runs Mypy and Black upon PR into main\n\n## Neural network app\nA pre-trained instance of the class is hosted on [Google Cloud Run](https://handwritten-digit-recognizer-app-569320861368.asia-east1.run.app/) and provides a nifty user interface.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmagnushelliesen%2Fneural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmagnushelliesen%2Fneural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmagnushelliesen%2Fneural-network/lists"}