{"id":16691937,"url":"https://github.com/ravimashru/deno-nets","last_synced_at":"2026-03-10T05:02:06.256Z","repository":{"id":52273585,"uuid":"306291050","full_name":"ravimashru/deno-nets","owner":"ravimashru","description":"Create, train and use deep neural networks using Typescript in Deno","archived":false,"fork":false,"pushed_at":"2021-01-30T17:01:14.000Z","size":12440,"stargazers_count":4,"open_issues_count":2,"forks_count":5,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-09-22T21:54:02.419Z","etag":null,"topics":["deno","hacktoberfest","neural-networks"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ravimashru.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}},"created_at":"2020-10-22T09:43:21.000Z","updated_at":"2022-08-19T23:00:26.000Z","dependencies_parsed_at":"2022-09-11T12:42:05.499Z","dependency_job_id":null,"html_url":"https://github.com/ravimashru/deno-nets","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/ravimashru/deno-nets","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ravimashru%2Fdeno-nets","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ravimashru%2Fdeno-nets/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ravimashru%2Fdeno-nets/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ravimashru%2Fdeno-nets/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ravimashru","download_url":"https://codeload.github.com/ravimashru/deno-nets/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ravimashru%2Fdeno-nets/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30325598,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T01:36:58.598Z","status":"online","status_checked_at":"2026-03-10T02:00:06.579Z","response_time":106,"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":["deno","hacktoberfest","neural-networks"],"created_at":"2024-10-12T16:10:48.898Z","updated_at":"2026-03-10T05:02:06.221Z","avatar_url":"https://github.com/ravimashru.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# deno-nets\nCreate, train and use neural networks using Typescript in Deno\n\nGoal: create a Deno module with an interface like Scikit-learn to create, train and use neural networks\n\nPlan: work on this during the upcoming [Deno Hacktoberfest](https://organize.mlh.io/participants/events/5363-nest-land-hacktoberfest-online-meetup-with-ryan-dahl-sam-williams-and-michael-spengler)\n\n## MVP\n- [ ] Dense Layers\n- [ ] SGD optimizer\n- [ ] Ability to define activation functions (in hidden layers and output layer)\n- [ ] Basic metrics (e.g. RMSE for regression, accuracy for classification)\n- [ ] A network that achieves decent test accuracy on [MNIST handwritten digits](http://yann.lecun.com/exdb/mnist/)\n\n## Potential Features\n- [ ] Convolutional Layers\n- [ ] Different optimizers (e.g. AdaGrad, Adam, SGD with momentum, etc.)\n- [ ] Advanced metrics (e.g. F1 score)\n\n## Potential Interface\n```typescript\nconst net = new Network(input_dimensions=5, output_dimensions=1, hidden_layers=[5, 6])  \n\n// X has 2 dimensions (batch_size, input_dimensions)\n// y as 2 dimensions (batch_size, output_dimensions)\nnet.train(X, y)   \n\n// X has 2 dimensions (batch_size, input_dimensions)\nnet.predict(X)\n```\n\n## Loading MNIST Handwritten Digits data\nThis repository contains the [MNIST handritten digits](http://yann.lecun.com/exdb/mnist/) dataset in the `data` directory to train the network on. The dataset is compressed (gzip) and needs to be uncompressed before it can be used.\n\nThe `MNISTDataLoader` class can be used as follows to load data in a format that can be used with the neural network directly:\n\n```typescript\n// Create an instance of the loader class\nconst loader = new MNISTDataLoader();\n\n// Load the training data\nconst [X_train, y_train] = await loader.load_train();\n\n// Load the test data\nconst [X_test, y_test] = await loader.load_test();\n```\n\nTo check if everything works, run the data loader tests:\n```shell\n$ deno run --allow-read deno-loader-test.ts\n```\n\n\n## Reference\n- http://neuralnetworksanddeeplearning.com/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fravimashru%2Fdeno-nets","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fravimashru%2Fdeno-nets","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fravimashru%2Fdeno-nets/lists"}