{"id":20789531,"url":"https://github.com/noahfeldt/ann-from-scratch","last_synced_at":"2026-04-12T12:38:15.136Z","repository":{"id":197066389,"uuid":"678097146","full_name":"NoahFeldt/ANN-From-Scratch","owner":"NoahFeldt","description":"Implementation of a multi layer perceptron artificial neural network from scratch that is tested using the MNIST dataset.","archived":false,"fork":false,"pushed_at":"2023-09-28T19:14:45.000Z","size":389,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-18T10:27:21.335Z","etag":null,"topics":["artificial-intelligence","artificial-neural-networks","image-classification","machine-learning","ml","mlp","mlp-classifier","mnist","mnist-classification","mnist-dataset","mnist-handwriting-recognition","multi-layer-perceptron","neural-network","nn","numpy","python","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","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/NoahFeldt.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}},"created_at":"2023-08-13T17:06:06.000Z","updated_at":"2023-10-07T08:22:01.000Z","dependencies_parsed_at":null,"dependency_job_id":"4710fced-9a9b-40bf-96ee-79cdb8edcf7d","html_url":"https://github.com/NoahFeldt/ANN-From-Scratch","commit_stats":null,"previous_names":["noahfeldt/ann-from-scratch"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NoahFeldt%2FANN-From-Scratch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NoahFeldt%2FANN-From-Scratch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NoahFeldt%2FANN-From-Scratch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NoahFeldt%2FANN-From-Scratch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NoahFeldt","download_url":"https://codeload.github.com/NoahFeldt/ANN-From-Scratch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243135403,"owners_count":20241961,"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-intelligence","artificial-neural-networks","image-classification","machine-learning","ml","mlp","mlp-classifier","mnist","mnist-classification","mnist-dataset","mnist-handwriting-recognition","multi-layer-perceptron","neural-network","nn","numpy","python","reinforcement-learning"],"created_at":"2024-11-17T15:24:44.532Z","updated_at":"2026-04-12T12:38:10.097Z","avatar_url":"https://github.com/NoahFeldt.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ANN-From-Scratch\nImplementation of a multi layer perceptron artificial neural network from scratch that is tested using the MNIST dataset.\n\n## Prerequisites\n\nThe [NumPy](https://github.com/numpy/numpy) module is used for numerical vector and matrix calculations:\n\n```bash\npip install numpy\n```\n\nThe [Keras](https://github.com/keras-team/keras) module is used to import the MNIST dataset:\n\n```bash\npip install keras\n```\n\nThe [tqdm](https://github.com/tqdm/tqdm) module is used for creating the progress bar:\n\n```bash\npip install tqdm\n```\n\n## Design choices \n\nThe neural network implementation uses the following design choices:\n\n* Sigmoid activation function.\n\n* Xavier Glorot initialization of the weights.\n\n* Zero initialization of the biases.\n\n* Mean squared error cost function.\n\n## Usage\n\nThe neural network implementation, can be found in the `ann.py` module where the `NeuralNetwork` class exists.\n\nTo test the neural network on the MNIST dataset, run the `mnist.py` file. This script will train and test a neural network with the given parameters.\n\n## Results\n\nThe neural network reaches an accuracy of about 90.5 % on MNIST dataset with the parameters used in the `mnist.py` file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnoahfeldt%2Fann-from-scratch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnoahfeldt%2Fann-from-scratch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnoahfeldt%2Fann-from-scratch/lists"}