{"id":15952833,"url":"https://github.com/jedrazb/python-neural-network","last_synced_at":"2026-02-01T09:31:45.916Z","repository":{"id":113654252,"uuid":"183989560","full_name":"jedrazb/python-neural-network","owner":"jedrazb","description":"Simple implementation of MLP neural network in NumPy with supporting examples","archived":false,"fork":false,"pushed_at":"2020-11-21T17:35:55.000Z","size":11346,"stargazers_count":3,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-28T23:42:43.581Z","etag":null,"topics":["iris","iris-dataset","machine-learning","mlp","mlp-classifier","mlp-network","neural-network","neural-networks","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/jedrazb.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":"2019-04-29T02:55:50.000Z","updated_at":"2025-03-27T13:41:47.000Z","dependencies_parsed_at":null,"dependency_job_id":"3fbd9ee4-983e-4632-945c-cf401894bb4a","html_url":"https://github.com/jedrazb/python-neural-network","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jedrazb/python-neural-network","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Fpython-neural-network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Fpython-neural-network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Fpython-neural-network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Fpython-neural-network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jedrazb","download_url":"https://codeload.github.com/jedrazb/python-neural-network/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jedrazb%2Fpython-neural-network/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28975214,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-01T08:16:14.655Z","status":"ssl_error","status_checked_at":"2026-02-01T08:06:51.373Z","response_time":56,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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":["iris","iris-dataset","machine-learning","mlp","mlp-classifier","mlp-network","neural-network","neural-networks","python"],"created_at":"2024-10-07T13:09:57.471Z","updated_at":"2026-02-01T09:31:45.900Z","avatar_url":"https://github.com/jedrazb.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MLP neural network library implemented using numpy\n\n\n\n## General \n\nThis a fully functional feedforward neural network library. The implemented features are:\n- loss functions: cross entropy, mean squared error\n- layers: linear, sigmoid, ReLU\n- network with forward and backpropagation\n- function to one hot encode labels\n- confussion matrix visualiser\n\nThere are two demos to demonstrate capabilities of the library:\n- iris dataset classifier\n- handwritten digits (mnist) classifier\n\nThere are lots of comments in the code explaining the details\n\n## Rquirements\n\n- python 3.x\n- numpy\n- matplotlib\n\n## Installation \n\nTo install required dependencies: `make install`.\n\n## Demo (iris dataset)\n\nTo run the demo: `python3 iris_demo.py`.\n\nThe demo is based on the [iris dataset](https://en.wikipedia.org/wiki/Iris_flower_data_set), the dataset can be found in `dataset/iris/`. It consists of 150 entries. \n\nThe accuracy obtained on the validation set is: 98.7%.\n\nIn the demo data is shuffled split into train and validation datasets, the netowork is trained and the performance is displayed as a confusion matrix:\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://i.ibb.co/RBBWTTJ/Screenshot-2019-05-05-at-12-50-43.png\" width=\"400\"\u003e\u003c/p\u003e\n\n## Demo (handwritten digits mnist dataset)\n\nTo run the demo: `python3 digits_mnist_demo.py`.\n\nThis demo is based on [mnist digits dataset](http://yann.lecun.com/exdb/mnist/), the dataset can be found in `dataset/digits_mnist/`. It consists of 60000 train images and 10000 test images.\n\nThe accuracy obtained on the test set is: 97.8%.\n\nExample network architecture:\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://www.newtownpartners.com/wp-content/uploads/2018/08/jon-jon-4.png\" width=\"400\"\u003e\u003c/p\u003e\n\nExample confusion matrix:\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"https://i.ibb.co/fvdh3Kt/Screenshot-2019-05-05-at-12-35-39.png\" width=\"400\"\u003e\u003c/p\u003e\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjedrazb%2Fpython-neural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjedrazb%2Fpython-neural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjedrazb%2Fpython-neural-network/lists"}