{"id":16653367,"url":"https://github.com/mattmoony/convnet_mnist","last_synced_at":"2026-04-20T13:34:04.372Z","repository":{"id":105902322,"uuid":"200305467","full_name":"MattMoony/convnet_mnist","owner":"MattMoony","description":"Simple convolutional neural network (purely numpy) to classify the original MNIST dataset. My first project with a convnet. 🖼 ","archived":false,"fork":false,"pushed_at":"2021-09-16T17:26:32.000Z","size":927,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-19T10:31:16.715Z","etag":null,"topics":["ann","artificial-neural-network","batch-normalization","convnet","convolutional-neural-network","datascience","dropout","machine-learning","mnist","neural-network","pooling","stochastic-gradient-descent"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/MattMoony.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":"2019-08-02T22:37:00.000Z","updated_at":"2023-12-19T12:56:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"d74bab50-6711-4bde-8252-ed8db8f5c792","html_url":"https://github.com/MattMoony/convnet_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%2Fconvnet_mnist","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fconvnet_mnist/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fconvnet_mnist/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MattMoony%2Fconvnet_mnist/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MattMoony","download_url":"https://codeload.github.com/MattMoony/convnet_mnist/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243261139,"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":["ann","artificial-neural-network","batch-normalization","convnet","convolutional-neural-network","datascience","dropout","machine-learning","mnist","neural-network","pooling","stochastic-gradient-descent"],"created_at":"2024-10-12T09:44:08.115Z","updated_at":"2025-12-27T17:12:30.141Z","avatar_url":"https://github.com/MattMoony.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ConvNet - MNIST Dataset\n_Simple ConvNet classifying MNIST data_\n\n---\n\n## About\n\nThis is supposed to be a little test project. I want to play around with convolutional layers, pooling layers, normalization strategies (dropout, batch normalization), training algorithms (Vanilla SGD, SGD w. Momentum, etc.) and much more.\n\n## To-Do\n\n* [x] Dataset preparation\n* [x] Simple weight initialization\n* [x] Advanced weigth initialization (Xavier initialization, etc.)\n* [x] Convolution-Function\n* [ ] Pooling Layers (Max-Pooling, Average-Pooling, etc.)\n* [ ] Dropout\n* [ ] Batch Normalization\n* [x] Activation-Function (ReLU)\n* [x] Loss-Function (Cross Entropy)\n* [x] Gradient-Computation Function\n* [x] Stochastic Mini Batch Gradient Descent\n* [x] Advanced SGD (Momentum, RMSprop, Adam, etc.)\n* [x] J/epoch-Graph\n* [x] Graphical representation of convolutional Layers\n* [x] Prediction-Function\n* [x] Model evaluation (Accuracy)\n* _... probably more to come ..._\n\n## Results\n\nBest accuracy so far: **93.14%**\n\n![J/Epoch-Graphs](media/JEpochGraph3.png)\n_J/Epoch-Graph over 1024 iterations ..._\n\n![Convolutions1](media/conv_ws_acts.png)\n![Convolutions2](media/conv_ws_acts2.png)\n_Convolutional weights \u0026 activations (examples: 8, 5)_\n\n---\n\n... MattMoony (August, 2019)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmattmoony%2Fconvnet_mnist","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmattmoony%2Fconvnet_mnist","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmattmoony%2Fconvnet_mnist/lists"}