{"id":24953363,"url":"https://github.com/iamfarrokhnejad/neural-network","last_synced_at":"2026-05-11T02:15:03.605Z","repository":{"id":270630089,"uuid":"910971827","full_name":"IAmFarrokhnejad/Neural-Network","owner":"IAmFarrokhnejad","description":"A simple neural network without reliance on any NN library.","archived":false,"fork":false,"pushed_at":"2025-01-19T21:21:13.000Z","size":6,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-03T03:34:46.341Z","etag":null,"topics":["classification","matplotlib","mnist","mnist-classification","mnist-dataset","mnist-handwriting-recognition","neural-network","neural-networks","neuralnetwork","neuralnetworks","numpy","pandas","python"],"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/IAmFarrokhnejad.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":"2025-01-02T00:06:01.000Z","updated_at":"2025-01-19T21:21:14.000Z","dependencies_parsed_at":"2025-01-02T01:33:18.258Z","dependency_job_id":null,"html_url":"https://github.com/IAmFarrokhnejad/Neural-Network","commit_stats":null,"previous_names":["iamfarrokhnejad/neural-network"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IAmFarrokhnejad%2FNeural-Network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IAmFarrokhnejad%2FNeural-Network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IAmFarrokhnejad%2FNeural-Network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/IAmFarrokhnejad%2FNeural-Network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/IAmFarrokhnejad","download_url":"https://codeload.github.com/IAmFarrokhnejad/Neural-Network/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246093097,"owners_count":20722395,"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":["classification","matplotlib","mnist","mnist-classification","mnist-dataset","mnist-handwriting-recognition","neural-network","neural-networks","neuralnetwork","neuralnetworks","numpy","pandas","python"],"created_at":"2025-02-03T03:35:17.187Z","updated_at":"2026-05-11T02:14:58.579Z","avatar_url":"https://github.com/IAmFarrokhnejad.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Network\n\n\n## Overview\nThis repository contains the implementation of a neural network developed from scratch in Python without using any deep learning libraries (e.g., PyTorch, TensorFlow). The project showcases the process of building, training, and evaluating a custom neural network.\n\n## Features\n- Implementation of feedforward and backpropagation algorithms.\n- Modular architecture with customizable activation functions, layers, and optimizers.\n- Training accuracy of up to 92.63% over 2500 iterations.\n\n## Prerequisites\nEnsure you have the following installed on your system:\n- Python 3.8+\n- MNIST dataset: https://www.kaggle.com/datasets/oddrationale/mnist-in-csv\n- Required libraries (install via `requirements.txt`):\n  ```bash\n  pip install pandas\n  ```\n\n## Usage\n\n### 1. Clone the Repository\n```bash\ngit clone https://github.com/IAmFarrokhnejad/Neural-Network\ncd your-repo-name\n```\n\n### 2. Prepare the Data\nPlace your dataset files in the `data/` directory. Ensure that the data is preprocessed as required by the training script.\n\n### 3. Train the Neural Network\nRun the training script to start the training process:\n```bash\npython mnist.py\n```\nTraining logs, including iteration-wise accuracy, will be displayed in the console.\n\n## Sample Output\nExample of training accuracy progression:\n```\nIteration 0, Accuracy: 0.1285\nIteration 1000, Accuracy: 0.9147\nIteration 2500, Accuracy: 0.9263\nIteration 7000, Accuracy: 0.9378\nIteration 9990, Accuracy: 0.9429\n\n```\n\n## Contributions\nContributions are welcome! Feel free to open an issue or submit a pull request.\n\n## License\nThis project is licensed under the MIT License. See `LICENSE` for details.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiamfarrokhnejad%2Fneural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiamfarrokhnejad%2Fneural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiamfarrokhnejad%2Fneural-network/lists"}