{"id":28224188,"url":"https://github.com/danishayman/low-level-tensorflow","last_synced_at":"2026-05-03T09:38:32.279Z","repository":{"id":270370948,"uuid":"786409995","full_name":"danishayman/Low-Level-Tensorflow","owner":"danishayman","description":"A low-level TensorFlow implementation of a neural network model using gradient descent optimization.","archived":false,"fork":false,"pushed_at":"2025-05-11T06:51:29.000Z","size":264,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-18T09:11:31.502Z","etag":null,"topics":["gradient-descent","neural-network","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/danishayman.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":"2024-04-14T11:30:53.000Z","updated_at":"2025-05-11T06:57:57.000Z","dependencies_parsed_at":"2024-12-31T15:35:24.965Z","dependency_job_id":null,"html_url":"https://github.com/danishayman/Low-Level-Tensorflow","commit_stats":null,"previous_names":["danishayman/low-level-tensorflow"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/danishayman/Low-Level-Tensorflow","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danishayman%2FLow-Level-Tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danishayman%2FLow-Level-Tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danishayman%2FLow-Level-Tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danishayman%2FLow-Level-Tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danishayman","download_url":"https://codeload.github.com/danishayman/Low-Level-Tensorflow/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danishayman%2FLow-Level-Tensorflow/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259389537,"owners_count":22850025,"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":["gradient-descent","neural-network","tensorflow"],"created_at":"2025-05-18T09:11:09.537Z","updated_at":"2026-05-03T09:38:32.220Z","avatar_url":"https://github.com/danishayman.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Network Implementation with TensorFlow 🧠\n\nA low-level TensorFlow implementation of a neural network model using gradient descent optimization.\n\n---\n\n## 📋 Project Overview\n\nThis project implements a neural network model from scratch using TensorFlow's low-level API. The implementation includes:\n- Custom forward propagation\n- Gradient descent optimization\n- Early stopping mechanism\n- Model evaluation metrics\n\n---\n\n## 📊 Dataset\n\nThe dataset contains binary classification data with 5 input features. Distribution:\n- Training set: 700 samples\n- Validation set: 100 samples\n- Test set: 200 samples\n\n---\n\n## 🏗️ Model Architecture\n\n- Input layer: 5 neurons\n- Hidden layer: 15 neurons with ReLU activation\n- Output layer: 1 neuron with sigmoid activation\n- Loss function: Mean Squared Error\n\n---\n\n## 🛠️ Implementation Details\n\n### Key Components\n\n1. Data Processing: \n   - 📈 Standard scaling normalization\n   - 🔄 70-10-20 train-validation-test split\n\n2. Model Functions:\n   - 🔜 `forward()`: Implements forward propagation\n   - 📉 `loss_fn()`: Calculates MSE loss\n   - 🎯 `train()`: Single training step using gradient tape\n   - 🔄 `fit()`: Training loop with early stopping\n\n3. Training Parameters:\n   - Learning rate: 0.01\n   - Batch size: 16\n   - Maximum epochs: 100\n   - Early stopping patience: 5\n\n---\n\n## 📈 Results\n\n- Final test loss: 0.268303\n- Classification metrics:\n  - Accuracy: 58%\n  - Precision: 59%\n  - Recall: 58%\n  - F1-score: 55%\n\n---\n\n## 🚀 Getting Started\n\n### Prerequisites\n\n- Python 3.x\n- Git\n\n### Clone the Repository\n\n```bash\ngit clone https://github.com/danishayman/Low-Level-Tensorflow.git\ncd low-level-tensorflow\n```\n\n### Install Dependencies\n\n```bash\npip install -r requirements.txt\n```\n\nThe required packages are:\n- TensorFlow 2.x\n- pandas\n- numpy\n- scikit-learn\n- matplotlib\n- jupyter\n\n---\n\n## 🚀 Usage\n\n1. Start Jupyter Notebook:\n```bash\njupyter notebook\n```\n\n2. Open the `Low_Level_TF.ipynb` notebook:\n```python\n# Load and preprocess data\ndataset = pd.read_csv('classification_dataset.csv')\n```\n\n3. Train model:\n```python\ntrain_losses, valid_losses = fit(model, optimizer, train_data, valid_data, \n                               weights, biases, epochs, batch_size, patience)\n```\n\n---\n\n## 📦 Requirements\n\nSee `requirements.txt` for a complete list of dependencies.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanishayman%2Flow-level-tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanishayman%2Flow-level-tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanishayman%2Flow-level-tensorflow/lists"}