{"id":18425421,"url":"https://github.com/burnpiro/elm-pure","last_synced_at":"2025-07-05T22:35:46.275Z","repository":{"id":63301346,"uuid":"244227435","full_name":"burnpiro/elm-pure","owner":"burnpiro","description":"Pure implementation of ELM (Extreme Learning Machine) in python (just with numpy)","archived":false,"fork":false,"pushed_at":"2020-05-13T20:25:14.000Z","size":184,"stargazers_count":44,"open_issues_count":3,"forks_count":25,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-07T16:41:05.739Z","etag":null,"topics":["extreme-learning-machine","machine-learning","ml"],"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/burnpiro.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}},"created_at":"2020-03-01T21:36:00.000Z","updated_at":"2025-01-06T14:36:12.000Z","dependencies_parsed_at":"2022-11-16T15:31:55.156Z","dependency_job_id":null,"html_url":"https://github.com/burnpiro/elm-pure","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/burnpiro/elm-pure","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burnpiro%2Felm-pure","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burnpiro%2Felm-pure/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burnpiro%2Felm-pure/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burnpiro%2Felm-pure/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/burnpiro","download_url":"https://codeload.github.com/burnpiro/elm-pure/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/burnpiro%2Felm-pure/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263818949,"owners_count":23516092,"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":["extreme-learning-machine","machine-learning","ml"],"created_at":"2024-11-06T05:03:51.816Z","updated_at":"2025-07-05T22:35:46.255Z","avatar_url":"https://github.com/burnpiro.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Minimalist implementation of Extreme Learning Machine\n\n![ELM structure](./ELM.png)\n\nThis is an implementation of Extreme Learning Machine as defined in [Extreme Learning Machine: A New LearningScheme of Feedforward Neural Networks](https://www.researchgate.net/publication/4116697_Extreme_learning_machine_A_new_learning_scheme_of_feedforward_neural_networks) paper by Guang-Bin Huang, Qin-Yu Zhu, and Chee-Kheong Siew\n\n## Dependencies\n\nPlease always check `requirements.txt` for current dependencies\n\n- Python 3.7\n- Numpy 1.17\n- Keras 2.3\n\nKeras are not used to design model. It's just a great source of datasets :P Feel free remove it and use your own dataset.\n\n## Usage\nCurrently tests are run on MNIST dataset (it's a hand-written digits dataset). You can change that inside `test.py` file. \n\n```bash\npython test.py\n```\n\nIf you want, you can load weights into model by passing them as arguments:\n- `beta_init`\n- `w_init`\n- `bias_init`\n\nYou can also change `activation` and `loss` function just pass:\n- `activation` - `sigmoid`, `fourier`, `hardlimit`\n- `loss` - `mse` (mean square error), `mae` (mean absolute error)\n\n### Important\nWatch out for computation complexity. Each time you try to __fit__ the model it has to do expensive matrix inversion [Moore–Penrose inverse](https://en.wikipedia.org/wiki/Moore%E2%80%93Penrose_inverse). MNIST dataset has 60k images (__H__ matrix has size of __60000x1024__) and takes around 8.5s to inverse on i7-7820X CPU. Remember about it when changing dataset or number of hidden layers\n\n## Todo\n- Implement saving/loading model (`h5py`)\n- Implement tests\n- Implement performance metric","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fburnpiro%2Felm-pure","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fburnpiro%2Felm-pure","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fburnpiro%2Felm-pure/lists"}