{"id":24300042,"url":"https://github.com/nishatrhythm/machine-learning","last_synced_at":"2025-03-06T12:16:50.088Z","repository":{"id":272713521,"uuid":"915943619","full_name":"nishatrhythm/Machine-Learning","owner":"nishatrhythm","description":"A dynamic repository showcasing practical Machine Learning projects, featuring cutting-edge techniques, model training, and hyperparameter optimization for impactful insights.","archived":false,"fork":false,"pushed_at":"2025-01-16T06:24:11.000Z","size":2022,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-16T07:31:30.841Z","etag":null,"topics":["hyperparameter-optimization","machine-learning"],"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/nishatrhythm.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":"2025-01-13T06:38:42.000Z","updated_at":"2025-01-16T06:24:12.000Z","dependencies_parsed_at":"2025-01-16T07:31:38.958Z","dependency_job_id":"6be7867e-363a-41b5-b24a-aeb809b26722","html_url":"https://github.com/nishatrhythm/Machine-Learning","commit_stats":null,"previous_names":["nishatrhythm/machine-learning"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nishatrhythm%2FMachine-Learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nishatrhythm%2FMachine-Learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nishatrhythm%2FMachine-Learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nishatrhythm%2FMachine-Learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nishatrhythm","download_url":"https://codeload.github.com/nishatrhythm/Machine-Learning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242206044,"owners_count":20089255,"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":["hyperparameter-optimization","machine-learning"],"created_at":"2025-01-16T22:34:54.265Z","updated_at":"2025-03-06T12:16:50.066Z","avatar_url":"https://github.com/nishatrhythm.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Hyperparameter Optimization for LSTM on Daily Minimum Temperatures Dataset\n\nThis repository demonstrates hyperparameter optimization for Long Short-Term Memory (LSTM) networks on the **Daily Minimum Temperatures Dataset**. The objective is to predict the next day's temperature using time-series data and evaluate the impact of various hyperparameters on the model's performance.\n\n## Dataset\n\nThe dataset used is the **Daily Minimum Temperatures Dataset**, which contains daily minimum temperatures recorded in Melbourne, Australia. It spans from 1981 to 1990 and can be directly downloaded from [this link](https://raw.githubusercontent.com/jbrownlee/Datasets/master/daily-min-temperatures.csv).\n\n## Features\n\n- **Dynamic hyperparameter optimization** using combinations of:\n  - Activation Functions: `tanh`, `relu`\n  - Number of Neurons: `50`, `100`\n  - Dropout Rates: `0.2`, `0.3`\n  - Number of Layers: `1`, `2`\n  - Optimizers: `adam`, `rmsprop`\n  - Learning Rates: `0.001`, `0.01`\n  - Epochs: `20`, `30`\n- Results logged into CSV files:\n  - `hyperparameter_results.csv`: Contains metrics for all hyperparameter combinations.\n  - `best_hyperparameters.csv`: Contains the best-performing hyperparameter configuration.\n- Visualization of training and validation losses for the best model.\n- **Best model saved** as `best_lstm_model.h5` for future use.\n\n## Execution Environment\n\nThis project was executed on **Google Colab** using the **v2-8 TPU**. The total execution time was approximately **5378.465 seconds**.\n\n## Files\n\n- **`hyperparameter_results.csv`**: Contains performance metrics (MSE, MAE) for all hyperparameter combinations.\n- **`best_hyperparameters.csv`**: Contains the best-performing hyperparameter configuration based on MSE.\n- **`best_lstm_model.h5`**: The trained LSTM model using the best hyperparameters.\n\n## Results\n\nThe best-performing hyperparameters are as follows:\n\n| Activation Function | Number of Neurons | Dropout Rate | Number of Layers | Optimizer | Learning Rate | Epochs | Test Loss | MAE    | MSE    |\n|---------------------|-------------------|--------------|------------------|-----------|---------------|--------|-----------|--------|--------|\n| `tanh`             | 100               | 0.2          | 2                | `rmsprop` | 0.01          | 20     | 0.007019  | 0.0659 | 0.0070 |\n\n## Performance\n\n- **Test Loss**: `0.007019`\n- **Mean Absolute Error (MAE)**: `0.0659`\n- **Mean Squared Error (MSE)**: `0.0070`\n\n## Visualization\n\n![Loss Curve](Hyperparameter%20Optimization%20for%20LSTM/loss_curve.png)  \nThe graph shows the training and validation loss for the best model over epochs.\n\n## References\n\n- Dataset: [Daily Minimum Temperatures Dataset](https://github.com/jbrownlee/Datasets)\n- LSTM implementation and hyperparameter optimization techniques.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnishatrhythm%2Fmachine-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnishatrhythm%2Fmachine-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnishatrhythm%2Fmachine-learning/lists"}