{"id":51220960,"url":"https://github.com/sankhya007/demo_neural","last_synced_at":"2026-06-28T07:03:06.134Z","repository":{"id":321450513,"uuid":"1085893833","full_name":"sankhya007/demo_neural","owner":"sankhya007","description":null,"archived":false,"fork":false,"pushed_at":"2025-10-29T17:05:46.000Z","size":17,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-29T19:08:02.955Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/sankhya007.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-29T16:49:19.000Z","updated_at":"2025-10-29T17:05:50.000Z","dependencies_parsed_at":"2025-10-29T19:08:06.750Z","dependency_job_id":"68542a03-3a6a-4add-b946-208604e9ef82","html_url":"https://github.com/sankhya007/demo_neural","commit_stats":null,"previous_names":["sankhya007/demo_neural"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/sankhya007/demo_neural","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fdemo_neural","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fdemo_neural/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fdemo_neural/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fdemo_neural/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sankhya007","download_url":"https://codeload.github.com/sankhya007/demo_neural/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sankhya007%2Fdemo_neural/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34880191,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-28T02:00:05.809Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2026-06-28T07:03:05.239Z","updated_at":"2026-06-28T07:03:06.123Z","avatar_url":"https://github.com/sankhya007.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# 🧠 Neural Network from Scratch (Pure Python Implementation)\n\nA fully functional **neural network built from scratch in Python**, without relying on deep learning frameworks like TensorFlow or PyTorch.  \nThis project demonstrates the **core mechanics** behind neural networks — from forward propagation to backpropagation and gradient descent — with clean, modular, and well-documented code.\n\n\n## 🚀 Features\n\n✅ **Custom Neural Network Class** – Pure Python + NumPy implementation  \n✅ **Multiple Activation Functions** – ReLU, Sigmoid, and Tanh  \n✅ **Configurable Architecture** – Define any number of layers and neurons  \n✅ **Supports Both Tasks** – Classification \u0026 Regression  \n✅ **Mini-Batch Gradient Descent** – Efficient training  \n✅ **Real-Time Training Visualization** – Loss and accuracy plots  \n✅ **Comprehensive Evaluation Metrics** – Accuracy, MSE, and R² score  \n\n\n## 🧩 Project Structure\n\n```\n    neural_network_demo/\n    ├── neural_network.py      # Core neural network implementation (classification)\n    ├── main.py                # Demo for classification and regression\n    ├── requirements.txt       # Dependencies\n    ├── run.bat                # Run script for Windows\n    ├── run.sh                 # Run script for Linux/Mac\n    ├── README.md              # Project documentation\n    └── .gitignore             # Ignore unnecessary files\n```\n\n## ⚙️ Installation\n\n1️⃣ Clone the repository:\n```bash\ngit clone https://github.com/sankhya007/demo_neural.git\ncd demo_neural\n```\n\n2️⃣ Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n## ▶️ Usage\n\nRun the demo:\n    ```bash\n    python main.py\n    ```\n\nYou’ll see:\n    - Training progress with live updates every 100 epochs  \n    - Real-time loss and accuracy visualization  \n    - Final evaluation metrics for both classification and regression tasks  \n\n## 📊 Results\n\n- Achieves **~78% accuracy** on multi-class classification datasets  \n- Smooth convergence curves for both **loss** and **accuracy**\n- Regression model yields strong **R² performance** and low **MSE**  \n\n## 🧠 Concepts Covered\n\n- Forward Propagation  \n- Backpropagation  \n- Activation Functions (ReLU, Sigmoid, Tanh)  \n- Softmax Output for Multi-Class Problems  \n- Mini-Batch Gradient Descent  \n- Loss Functions (Cross-Entropy \u0026 MSE)  \n- Model Evaluation Metrics  \n\n## 📈 Example Visualizations\n\n- **Classification:** Loss \u0026 Accuracy curves over epochs  \n- **Regression:** Predicted vs Actual scatter plot with R² score  \n- **Training Diagnostics:** Validation loss tracking\n\n## 💡 Future Improvements\n\n- Add dropout and batch normalization  \n- Implement momentum and Adam optimizers  \n- Save and load trained model weights  \n- Extend to support convolutional layers\n\n\n## 🧑‍💻 Author\n\n**Sankhyapriyo Dey**  \n📧 [GitHub Profile](https://github.com/sankhya007)  \n\n## 🪪 License\n\nThis project is released under the **MIT License** – free to use and modify.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsankhya007%2Fdemo_neural","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsankhya007%2Fdemo_neural","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsankhya007%2Fdemo_neural/lists"}