{"id":16653377,"url":"https://github.com/mattmoony/ann_mnist","last_synced_at":"2026-04-09T21:47:33.517Z","repository":{"id":105902209,"uuid":"200739633","full_name":"MattMoony/ann_mnist","owner":"MattMoony","description":"Simple self-written ANN powered by NumPy to classify handwritten digits of the famous MNIST Dataset. ✍️","archived":false,"fork":false,"pushed_at":"2021-09-15T16:34:45.000Z","size":9403,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-19T10:31:19.377Z","etag":null,"topics":["adam","ann","deep-learning","learning-algorithm","machine-learning","ml","mnist","mnist-handwritten-digits","momentum","neural-net","neural-network","normalization","numpy","regularization","relu","sigmoid","tanh"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MattMoony.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":"2019-08-05T22:53:44.000Z","updated_at":"2023-12-19T12:56:23.000Z","dependencies_parsed_at":null,"dependency_job_id":"f71bcb09-af59-44ab-add1-e5da5aea875a","html_url":"https://github.com/MattMoony/ann_mnist","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fann_mnist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fann_mnist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fann_mnist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fann_mnist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MattMoony","download_url":"https://codeload.github.com/MattMoony/ann_mnist/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243261157,"owners_count":20262791,"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":["adam","ann","deep-learning","learning-algorithm","machine-learning","ml","mnist","mnist-handwritten-digits","momentum","neural-net","neural-network","normalization","numpy","regularization","relu","sigmoid","tanh"],"created_at":"2024-10-12T09:44:11.514Z","updated_at":"2025-12-26T21:49:03.852Z","avatar_url":"https://github.com/MattMoony.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"media/predictions.gif\" /\u003e\n\u003c/div\u003e\n\n\n\u003ch1 align=\"center\"\u003eMNIST Handwritten Digits:\u003cbr /\u003eA Simple ANN Classifier\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg alt=\"GitHub\" src=\"https://img.shields.io/github/license/MattMoony/ann_mnist?style=for-the-badge\"\u003e\n  \u003cimg alt=\"GitHub top language\" src=\"https://img.shields.io/github/languages/top/MattMoony/ann_mnist?style=for-the-badge\"\u003e\n  \u003cimg alt=\"GitHub Repo stars\" src=\"https://img.shields.io/github/stars/MattMoony/ann_mnist?style=for-the-badge\u0026color=cecece\"\u003e\n\u003c/p\u003e\n\n---\n\nA (hopefully) well-structured and easy to understand Jupyter notebook outlining some machine-learning basics with the help of a self-written adjustable *neural network* using purely the power of the brilliant [NumPy](https://numpy.org/) module. I originally decided against using any mainstream machine-learning modules such as [TensorFlow](https://github.com/tensorflow/tensorflow), [PyTorch](https://github.com/pytorch/pytorch), [Caffe](https://github.com/BVLC/caffe), etc. in order to acquire a *deeper understanding* about the mathematics and tech behind deep neural networks.\n\n\u003e Check out the notebook **[here](main.ipynb)!**\n\n## 📂 Repository Structure\n\nIf you want to clone this repository and run the notebook locally, then don't forget to install the dependencies, but most importantly, don't forget to also download the official [MNIST Handwritten Digits Dataset](http://yann.lecun.com/exdb/mnist/) and place it in the right place.\n\n```txt\nann_mnist/\n |- data/                           // dataset directory\n   |- t10k-images-idx3-ubyte.gz     // test features\n   |- t10k-labels-idx1-ubyte.gz     // test labels\n   |- train-images-idx3-ubyte.gz    // train features\n   |- train-labels-idx1-ubyte.gz    // train labels\n |- media/                          // media for README.md\n   |- ...\n |- snaps/                          // generated media\n   |- ...\n |- main.ipynb                      // main jupyter notebook\n |- main.py                         // legacy, 2019 code (fashion dataset)\n |- notebook.py                     // code-only version of notebook\n |- ...\n\n```\n\n## 🔍 Want More?\n\nSome of my other machine-learning repositories that I might do a makeover on soon as well. For references to other (perhaps more interesting) reads, check out the articles I linked to every now and then in the notebook.\n\n- [ConvNet - MNIST Dataset](https://github.com/MattMoony/convnet_mnist) [2019] ... Using a *convolutional neural network* to classify handwritten digits\n- [RNN (LSTM) - Goethe Texts](https://github.com/MattMoony/rnn-lstm_goethe-generation) [2019] ... Using a *recurrent neural network* (*long short term memory*) to generate characters in a \"Goethe-like\" manner\n- [ConvNet - Style Transer](https://github.com/MattMoony/convnet_style-transfer) [2019] ... Using PyTorch and the *VGG16* network to transfer artists' styles onto digital images\n- [ConvNet - Deep Dream](https://github.com/MattMoony/convnet_deep-dream) [2019] ... Using PyTorch and *GoogLeNet* to generate mind-blowing images using a neural network's \"imagination\"\n\n---\n\n... Matthias Monschein (September 2021)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmattmoony%2Fann_mnist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmattmoony%2Fann_mnist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmattmoony%2Fann_mnist/lists"}