{"id":19656940,"url":"https://github.com/yasinshafiei/fullyconnected-from-scratch","last_synced_at":"2026-05-17T06:45:27.509Z","repository":{"id":217555258,"uuid":"744206030","full_name":"YasinShafiei/FullyConnected-from-scratch","owner":"YasinShafiei","description":"Fully connected layer from scratch, with training on MNIST dataset ","archived":false,"fork":false,"pushed_at":"2024-04-18T12:46:10.000Z","size":13,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-02-27T02:24:38.906Z","etag":null,"topics":["adam-optimizer","ai","ann","artificial","artificial-intelligence","deep-learning","from-scratch","mlp","neural-network","numpy","perceptron","python"],"latest_commit_sha":null,"homepage":"","language":"Python","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/YasinShafiei.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":"2024-01-16T20:36:24.000Z","updated_at":"2024-01-25T00:20:50.000Z","dependencies_parsed_at":null,"dependency_job_id":"f46c4753-43ef-475f-b2cd-f809344e70a2","html_url":"https://github.com/YasinShafiei/FullyConnected-from-scratch","commit_stats":null,"previous_names":["yasinshafiei/fullyconnected-from-scratch"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/YasinShafiei/FullyConnected-from-scratch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YasinShafiei%2FFullyConnected-from-scratch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YasinShafiei%2FFullyConnected-from-scratch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YasinShafiei%2FFullyConnected-from-scratch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YasinShafiei%2FFullyConnected-from-scratch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/YasinShafiei","download_url":"https://codeload.github.com/YasinShafiei/FullyConnected-from-scratch/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/YasinShafiei%2FFullyConnected-from-scratch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002970,"owners_count":26083489,"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":"2025-10-10T02:00:06.843Z","response_time":62,"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":["adam-optimizer","ai","ann","artificial","artificial-intelligence","deep-learning","from-scratch","mlp","neural-network","numpy","perceptron","python"],"created_at":"2024-11-11T15:29:28.444Z","updated_at":"2025-10-10T06:39:45.701Z","avatar_url":"https://github.com/YasinShafiei.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FullyConnected neural network layer from scratch\nFully connected layer from scratch, with training on MNIST dataset. \u003cbr\u003e\nThe scripts are all for creating a Fully-Connected Neural Network layer and making a custom model. \u003cbr\u003e\nAlso the model trains on fully custom training loop. All the optimizer and loss function are written from scratch.\n\n## Results\nI implemented a MLP from scratch only using NumPy for model creation. Here are the results of the training:\u003cbr\u003e\n![Screenshot 2024-01-05 161138](https://github.com/YasinShafiei/FullyConnected-from-scratch/assets/91404054/b35b54a0-9bbf-42d2-9e27-47b546a8dac5)\n![Figure_1](https://github.com/YasinShafiei/FullyConnected-from-scratch/assets/91404054/bed1e2bc-854a-4696-b9e0-985829833872)\n![Figure_2](https://github.com/YasinShafiei/FullyConnected-from-scratch/assets/91404054/c30e52d1-484c-4a86-9f43-e40f9a874049)\n\n## Article:\nPlease go and checkout my article about this project for full explanations and detils:\nhttps://medium.com/@YasinShafiei/making-a-neural-network-fully-connected-layer-from-scratch-only-numpy-49bd7958b6f3\n\u003cbr\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyasinshafiei%2Ffullyconnected-from-scratch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyasinshafiei%2Ffullyconnected-from-scratch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyasinshafiei%2Ffullyconnected-from-scratch/lists"}