{"id":23975070,"url":"https://github.com/achronus/ai-experiments","last_synced_at":"2025-02-24T16:39:45.299Z","repository":{"id":271308033,"uuid":"913030433","full_name":"Achronus/ai-experiments","owner":"Achronus","description":"A repository for simple model implementations of research papers","archived":false,"fork":false,"pushed_at":"2025-02-08T17:59:31.000Z","size":103,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-08T18:32:55.425Z","etag":null,"topics":["ai-experiments","deep-learning","open-source-code","pytorch"],"latest_commit_sha":null,"homepage":"","language":"Python","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/Achronus.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":"2025-01-06T22:21:36.000Z","updated_at":"2025-02-08T17:59:33.000Z","dependencies_parsed_at":"2025-01-06T23:31:02.986Z","dependency_job_id":"d74d2e36-ad5b-407a-ab51-8a333fe9348e","html_url":"https://github.com/Achronus/ai-experiments","commit_stats":null,"previous_names":["achronus/ai-experiments"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achronus%2Fai-experiments","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achronus%2Fai-experiments/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achronus%2Fai-experiments/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Achronus%2Fai-experiments/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Achronus","download_url":"https://codeload.github.com/Achronus/ai-experiments/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":240516107,"owners_count":19813964,"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":["ai-experiments","deep-learning","open-source-code","pytorch"],"created_at":"2025-01-07T05:58:30.617Z","updated_at":"2025-02-24T16:39:45.279Z","avatar_url":"https://github.com/Achronus.png","language":"Python","readme":"# AI Experiments\n\nThe field of AI continues to grow at an exponential rate, with hundreds of new developments happening daily, making it extremely difficult to keep up with everything! There has also been a growing trend of reduced explainability and open-source models.\n\nThis repository is a step towards countering that. It houses a collection of important developments over the years with simple code implementations that are free to use and explore. Each one is accompanied by a Medium article that explains the development's fundamental details and code implementations.\n\nEach item is separated into a folder with a set of respective Python files. Some utility methods, such as activation functions, are stored in the root of the experiments folder for easier access to all individual experiments. Each folder has a corresponding `README.md` file highlighting a brief description of the development and structure.\n\nMy goal is to help push development for more efficient, high-performing, autonomous systems that improve the way we live our lives. All code will remain open-source and hopefully be an asset to the AI community.\n\nHappy reading and exploring! 😄\n\n## Experiments\n\n\u003c!-- Badge templates --\u003e\n\u003c!-- [![Project](https://img.shields.io/badge/Project-blue?style=for-the-badge\u0026logo=python\u0026logoColor=white)]() --\u003e\n\u003c!-- [![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge\u0026logo=medium\u0026logoColor=white)]() --\u003e\n\n| Item          | Project Link | Article Link |\n|---------------|--------------|--------------|\n| GLU Feed-Forward Networks | [![Project](https://img.shields.io/badge/Project-blue?style=for-the-badge\u0026logo=python\u0026logoColor=white)](/experiments/glu/) | [![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge\u0026logo=medium\u0026logoColor=white)](https://medium.com/@achronus/glu-a-simple-transformer-improvement-504e31c4252a) |\n| Titans | - | [![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge\u0026logo=medium\u0026logoColor=white)](https://medium.com/@achronus/titans-where-tokens-almost-live-forever-c995d9a84e0e) |\n| Liquid Neural Networks | [![Project](https://img.shields.io/badge/Project-blue?style=for-the-badge\u0026logo=python\u0026logoColor=white)](/experiments/lnn/) | [![Medium](https://img.shields.io/badge/Medium-12100E?style=for-the-badge\u0026logo=medium\u0026logoColor=white)](https://medium.com/@achronus/ltcs-with-ncps-an-alternative-to-large-ai-models-6c71729bd3d6) |\n\n\u003c!-- \n- Joint-embedding architectures\n- Energy-based models\n- Regularized methods (instead of contrastive)\n- Reduce RL (very sample inefficient) for model predictive control\n--\u003e\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fachronus%2Fai-experiments","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fachronus%2Fai-experiments","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fachronus%2Fai-experiments/lists"}