{"id":17632708,"url":"https://github.com/inventwithdean/cuda_mlp","last_synced_at":"2025-03-30T03:32:11.700Z","repository":{"id":251582285,"uuid":"837825263","full_name":"inventwithdean/CUDA_MLP","owner":"inventwithdean","description":"Implementation of a simple Multilayer Perceptron in pure CUDA","archived":false,"fork":false,"pushed_at":"2024-08-07T18:16:06.000Z","size":65,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-30T03:31:47.013Z","etag":null,"topics":["cuda","cuda-programming","deep-learning","neural-networks"],"latest_commit_sha":null,"homepage":"","language":"Cuda","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/inventwithdean.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":"2024-08-04T06:29:58.000Z","updated_at":"2024-08-07T18:16:09.000Z","dependencies_parsed_at":"2024-10-23T10:17:52.123Z","dependency_job_id":null,"html_url":"https://github.com/inventwithdean/CUDA_MLP","commit_stats":null,"previous_names":["inventwithdean/cuda_mlp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inventwithdean%2FCUDA_MLP","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inventwithdean%2FCUDA_MLP/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inventwithdean%2FCUDA_MLP/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/inventwithdean%2FCUDA_MLP/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/inventwithdean","download_url":"https://codeload.github.com/inventwithdean/CUDA_MLP/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246273533,"owners_count":20750904,"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":["cuda","cuda-programming","deep-learning","neural-networks"],"created_at":"2024-10-23T01:45:14.115Z","updated_at":"2025-03-30T03:32:11.681Z","avatar_url":"https://github.com/inventwithdean.png","language":"Cuda","readme":"This repository contains a pure CUDA C++ implementation of a Multilayer Perceptron (MLP) neural network with a Linear Regression Dataset with Apache 2 license on which the network attained a loss of 0.07. By building from the ground up, we gain a deep understanding of the inner workings of neural networks and the performance benefits of GPU acceleration.\n\n## Disclaimer: \n* This project is for educational purposes and may not be optimized for production use.\n\n## Features:\n\n* Pure CUDA C++ implementation: No external libraries or frameworks.\n* GPU acceleration: Leverage the power of GPUs for high performance.\n* Modular design: Clear separation of concerns for maintainability.\n  \n## Getting Started:\n* Clone the repository:\nBash\n`git clone https://github.com/inventwithdean/CUDA_MLP.git`\n\n* Set up CUDA environment: Ensure you have a CUDA-capable GPU and the necessary CUDA toolkit installed.\n* Compile the code: Use a CUDA-compatible compiler to build the project.\n* Run the executable: Execute the generated binary to run the MLP.\n## Structure:\n* include: Header files for classes and functions along with some kernels for MSE and ReLUs.\n* kernels: CUDA kernels for matrix related calculations\n* main.cu: Main file where dataset is loaded and Optimization loop happens\n* dataset.cu: A very simple and lightweight csv Dataset Loader class\n## Future Improvements:\n\n* Implementing Softmax and Convolutional layers.\n* Add optimization techniques like momentum.\n* Explore different activation functions and network architectures.\n* Improve performance through kernel tuning and optimization.\n## Contributing:\n\nFeel free to contribute to this project by:\n\n* Submitting bug reports\n* Suggesting new features\n* Improving the code\n* Writing documentation\n  \nLet's dive into the world of deep learning together!\n\n\n## License:\nMIT\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finventwithdean%2Fcuda_mlp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finventwithdean%2Fcuda_mlp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finventwithdean%2Fcuda_mlp/lists"}