{"id":26996299,"url":"https://github.com/jelhamm/deep-learning-for-channel-coding-mi-estimation","last_synced_at":"2025-10-09T16:18:02.369Z","repository":{"id":249490398,"uuid":"831527850","full_name":"jElhamm/Deep-Learning-for-Channel-Coding-MI-Estimation","owner":"jElhamm","description":"\"Simulations for the paper 'Deep Learning for Channel Coding via Neural Mutual Information Estimation' by Rick Fritschek, Rafael F. Schaefery, and Gerhard Wunder\"","archived":false,"fork":false,"pushed_at":"2024-08-08T13:35:35.000Z","size":552,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-24T18:17:51.798Z","etag":null,"topics":["channel-coding","decoding","deep-learning","encoder-decoder-model","encoding","ieee","ieee-journal","jupyter-notebook","machine-learning","model-training","mutual-information","mutual-information-estimation","mutual-information-neural-estimator","neural-network","paper-simulations","python","training-module"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1903.02865","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/jElhamm.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,"zenodo":null}},"created_at":"2024-07-20T20:28:03.000Z","updated_at":"2025-07-12T21:43:44.000Z","dependencies_parsed_at":"2025-07-24T15:35:52.026Z","dependency_job_id":"fdf3e887-df3e-4030-b9ba-8895b47c50ec","html_url":"https://github.com/jElhamm/Deep-Learning-for-Channel-Coding-MI-Estimation","commit_stats":null,"previous_names":["jelhamm/deep-learning-for-channel-coding-mi-estimation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/jElhamm/Deep-Learning-for-Channel-Coding-MI-Estimation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jElhamm%2FDeep-Learning-for-Channel-Coding-MI-Estimation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jElhamm%2FDeep-Learning-for-Channel-Coding-MI-Estimation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jElhamm%2FDeep-Learning-for-Channel-Coding-MI-Estimation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jElhamm%2FDeep-Learning-for-Channel-Coding-MI-Estimation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/jElhamm","download_url":"https://codeload.github.com/jElhamm/Deep-Learning-for-Channel-Coding-MI-Estimation/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/jElhamm%2FDeep-Learning-for-Channel-Coding-MI-Estimation/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279001769,"owners_count":26083171,"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":"2025-10-09T02:00:07.460Z","response_time":59,"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":["channel-coding","decoding","deep-learning","encoder-decoder-model","encoding","ieee","ieee-journal","jupyter-notebook","machine-learning","model-training","mutual-information","mutual-information-estimation","mutual-information-neural-estimator","neural-network","paper-simulations","python","training-module"],"created_at":"2025-04-04T01:18:09.563Z","updated_at":"2025-10-09T16:18:02.364Z","avatar_url":"https://github.com/jElhamm.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deep Learning for Channel Coding via Neural Mutual Information Estimation\n\n   This repository contains the implementation of the paper [**\"Deep Learning for Channel Coding via Neural Mutual Information Estimation\"**](https://github.com/jElhamm/Deep-Learning-for-Channel-Coding-MI-Estimation/blob/main/Deep%20Learning%20for%20Channel%20Coding%20via%20Neural.pdf).\n\n   The paper presents novel approaches for channel coding using neural networks, focusing on estimating [Mutual Information (MI)](https://en.wikipedia.org/wiki/Mutual_information) to optimize the performance of autoencoders under Rayleigh and Binary Input channels.\n   \n\n## Citation\n\n   If you find this repository useful in your research, please consider citing the following paper:\n\n```bibtex\n   @article{fritschek2019deep,\n      title={Deep Learning for Channel Coding via Neural Mutual Information Estimation},\n      author={Rick Fritschek, Rafael F. Schaefery, and Gerhard Wunder},\n      journal={IEEE Transactions on Information Theory},\n      volume={65},\n      number={4},\n      pages={2042--2059},\n      year={2019},\n      publisher={IEEE}\n   }\n```\n\n## Table of Contents\n   - [Overview](#overview)\n   - [File Descriptions](#file-descriptions)\n   - [Installation](#installation)\n   - [Usage](#usage)\n      - [Python Scripts](#python-scripts)\n      - [Jupyter Notebooks](#jupyter-notebooks)\n   - [Results](#results)\n   - [Requirements](#requirements)\n   - [Contributing](#contributing)\n   - [License](#license)\n\n## Overview\n\n   This repository includes:\n\n   * The original research paper in PDF format.\n   * Python implementations of the models and experiments discussed in the paper.\n   * Jupyter Notebooks for interactive exploration of the models.\n\n   The primary focus is on using *Mutual Information Neural Estimation (MINE)* to enhance the performance of autoencoders in channel coding tasks.\n   The code has been structured to facilitate ease of understanding and experimentation.\n\n## File Descriptions\n\n### [Python Scripts](Source%20Code/Python%20Sources%20File)\n\n   | Filename | Description |\n   | -------- | ----------- |\n   | [`AutoEncoder_Rayleigh_Channel_MINE.py`](Python%20Sources%20File/AutoEncoder_Rayleigh_Channel_MINE.py) | Implements the autoencoder architecture for Rayleigh channels with MI estimation using MINE. |\n   | [`Autoencoder_MINE_for_Binary_Input.py`](Python%20Sources%20File/Autoencoder_MINE_for_Binary%20Input.py) | Implements the autoencoder architecture optimized for binary input using MI estimation. |\n   | [`MINE_Encoder_Experimental_Model.py`](Python%20Sources%20File/MINE_Encoder_Experimental_Model.py) | Contains experimental models for testing the performance of MINE-based encoders under various channel conditions. |\n\n### [Jupyter Notebooks](Source%20Code/Jupyter%20Notebook%20Source%20File)\n\n   | Filename | Description |\n   | -------- | ----------- |\n   | [`AutoEncoder_Rayleigh_Channel_MINE.ipynb`](Jupyter%20Notebook%20Source%20File/AutoEncoder_Rayleigh_Channel_MINE.ipynb) | Interactive version of the Python script for Rayleigh channels, with step-by-step explanations and visualizations. |\n   | [`Autoencoder_MINE_for_Binary_Input.ipynb`](Jupyter%20Notebook%20Source%20File/Autoencoder_MINE_for_Binary_Input.ipynb) | Interactive version of the Python script optimized for binary input, allowing for parameter adjustments and result visualization. |\n   | [`MINE_Encoder_Experimental_Model.ipynb`](Jupyter%20Notebook%20Source%20File/MINE_Encoder_Experimental_Model.ipynb) | Interactive notebook for experimenting with different models and channel conditions, demonstrating the efficacy of the MINE approach. |\n\n## Installation\n\n1. **Clone the repository:**\n    ```bash\n    git clone https://github.com/jElhamm/Deep-Learning-for-Channel-Coding-MI-Estimation\n    cd Deep-Learning-for-Channel-Coding-via-Neural-Mutual-Information-Estimation\n    ```\n\n2. **Install the required packages:**\n    ```bash\n    pip install -r requirements.txt\n    ```\n\n3. **Open Jupyter Notebooks:**\n    ```bash\n    jupyter notebook\n    ```\n\n## Usage\n\n   To run the Python scripts directly:\n```bash\n   python AutoEncoder_Rayleigh_Channel_MINE.py\n   python Autoencoder_MINE_for_Binary_Input.py\n   python MINE_Encoder_Experimental_Model.py\n```\n\n   Alternatively, you can explore the Jupyter Notebooks to interactively execute and visualize the results.\n\n## Results\n\n   The results of the experiments conducted using these scripts and notebooks demonstrate the effectiveness of using MINE for channel coding tasks.\n   The implementation shows significant improvements in *Bit Error Rates (BER)* compared to traditional methods, particularly in noisy channel conditions.\n   Visualizations and detailed results are available within the respective Jupyter Notebooks.\n\n## Requirements\n\n   This project requires the following Python libraries:\n\n   | Library     | Version | Purpose                                           |\n   |-------------|---------|---------------------------------------------------|\n   |  numpy      | 1.26.4  | Used for numerical computations and array manipulations. |\n   |  scipy      | 1.13.1  | Used for scientific and technical computations. |\n   |  keras      | 3.4.1   | Used for building and training deep learning models. |\n   |  tensorflow | 2.17.0  | Provides the backend for deep learning models and computations. |\n   |  matplotlib | 3.7.1   | Used for creating visualizations and plots. |\n\nTo install these dependencies, you can use the [requirements.txt](requirements.txt) file included in the repository. Run the following command:\n\n```bash\npip install -r requirements.txt\n```\n\n## Contributing\n\n   We welcome contributions to this project! To contribute, please:\n\n   1. Fork the repository and clone your fork.\n   2. Create a new branch for your changes.\n   3. Make and test your changes, then commit them.\n   4. Push your changes to your fork and submit a pull request.\n\n## License\n\n   This repository is licensed under the BSD-3-Clause License.\n   See the [LICENSE](./LICENSE) file for more details.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjelhamm%2Fdeep-learning-for-channel-coding-mi-estimation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjelhamm%2Fdeep-learning-for-channel-coding-mi-estimation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjelhamm%2Fdeep-learning-for-channel-coding-mi-estimation/lists"}