{"id":29906080,"url":"https://github.com/dhruvbavaliya13/neural-network","last_synced_at":"2026-05-08T14:17:41.807Z","repository":{"id":305649021,"uuid":"1023477765","full_name":"DhruvBavaliya13/Neural-Network","owner":"DhruvBavaliya13","description":"This project demonstrates a simple neural network implementation from scratch using Python and NumPy, without relying on high-level frameworks like TensorFlow or PyTorch. It showcases a hands-on understanding of core neural network concepts including forward propagation, backpropagation, activation functions, loss calculation, and weight updates.","archived":false,"fork":false,"pushed_at":"2025-07-21T08:30:53.000Z","size":203,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-07-21T10:20:06.074Z","etag":null,"topics":["neural-network","python","scratch","tensorflow"],"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/DhruvBavaliya13.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}},"created_at":"2025-07-21T08:14:44.000Z","updated_at":"2025-07-21T08:30:57.000Z","dependencies_parsed_at":"2025-07-21T10:20:15.577Z","dependency_job_id":"4df9e2e9-1835-49cb-8a22-d683815f29b2","html_url":"https://github.com/DhruvBavaliya13/Neural-Network","commit_stats":null,"previous_names":["dhruvbavaliya13/neural-network"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/DhruvBavaliya13/Neural-Network","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DhruvBavaliya13%2FNeural-Network","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DhruvBavaliya13%2FNeural-Network/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DhruvBavaliya13%2FNeural-Network/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DhruvBavaliya13%2FNeural-Network/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/DhruvBavaliya13","download_url":"https://codeload.github.com/DhruvBavaliya13/Neural-Network/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/DhruvBavaliya13%2FNeural-Network/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268290776,"owners_count":24226649,"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","status":"online","status_checked_at":"2025-08-01T02:00:08.611Z","response_time":67,"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":["neural-network","python","scratch","tensorflow"],"created_at":"2025-08-01T20:16:59.799Z","updated_at":"2026-05-08T14:17:36.761Z","avatar_url":"https://github.com/DhruvBavaliya13.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Network from Scratch 🧠\n\nThis project is a basic implementation of a feedforward neural network built entirely from scratch using Python and NumPy — without any machine learning frameworks like TensorFlow, Keras, or PyTorch.\n\n## 🚀 Features\n\n- Simple feedforward neural network\n- Forward and backward propagation\n- Sigmoid activation function\n- Log loss \n- Written for learning and demonstration purposes\n\n## 🧠 How It Works\n\n1. **Initialize Weights** – Randomly initialize weights and biases.\n2. **Forward Pass** – Calculate outputs using activation functions.\n3. **Loss Calculation** – Compute error using Log Loss.\n4. **Backward Pass** – Adjust weights using the derivative of the loss.\n5. **Repeat** – Train over multiple epochs.\n\n## 📊 Example Output\n\nTrained on the dataset:\n\u003cimg width=\"1047\" height=\"61\" alt=\"image\" src=\"https://github.com/user-attachments/assets/670dd231-e528-4c86-b69e-ee49c0a507c5\" /\u003e\n\n## 📁 Project Structure\n    Neural-Network/\n        ├── insurance_data.csv     # Insurance small dataset\n        ├── NN_from_Scratch.ipynb  # Jupyter Notebook\n        ├── nn.jpg                 # NN explanation img\n        ├── logloss.png            # Log loss formula img\n        └── README.md              # Project documentation\n\n## 📦 Requirements\n\n- Python\n- NumPy\n- Pandas\n- sklearn\n\n## ▶️ How to run\n    python NN_from_Scratch.ipynb\n\n\n## 📚 Learning Goals\nThis project helped me understand:\n\nHow neural networks learn via backpropagation\n\nHow to implement gradient descent manually\n\nCore building blocks of deep learning\n\n🌟 Inspiration\nI built this project to solidify my understanding of neural networks at the mathematical and code level, and to learn how modern deep learning models are built from the ground up.\n\n🔗 Connect With Me\n📧 Dhruv Bavaliya\n📬 Feel free to contribute or fork this project if you're learning like me!\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdhruvbavaliya13%2Fneural-network","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdhruvbavaliya13%2Fneural-network","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdhruvbavaliya13%2Fneural-network/lists"}