{"id":37210890,"url":"https://github.com/vtech6/goml","last_synced_at":"2026-01-15T00:01:21.991Z","repository":{"id":201246541,"uuid":"705771049","full_name":"vtech6/goml","owner":"vtech6","description":"Neural Networks from scratch in Go (standard library only)","archived":false,"fork":false,"pushed_at":"2023-11-27T11:09:07.000Z","size":11116,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2023-11-28T11:40:29.691Z","etag":null,"topics":["binary-classification","deep-learning","from-scratch","golang","machine-learning","multilayer-perceptron","neural-network","vanilla"],"latest_commit_sha":null,"homepage":"","language":"Go","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/vtech6.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}},"created_at":"2023-10-16T16:54:48.000Z","updated_at":"2023-11-01T21:01:10.000Z","dependencies_parsed_at":"2023-11-06T14:29:13.548Z","dependency_job_id":"9368ec76-ecc5-4a5f-b094-285f272ef86d","html_url":"https://github.com/vtech6/goml","commit_stats":null,"previous_names":["vtech6/goml"],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/vtech6/goml","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vtech6%2Fgoml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vtech6%2Fgoml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vtech6%2Fgoml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vtech6%2Fgoml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vtech6","download_url":"https://codeload.github.com/vtech6/goml/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vtech6%2Fgoml/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28439605,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T22:37:52.437Z","status":"ssl_error","status_checked_at":"2026-01-14T22:37:31.496Z","response_time":107,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["binary-classification","deep-learning","from-scratch","golang","machine-learning","multilayer-perceptron","neural-network","vanilla"],"created_at":"2026-01-15T00:01:11.288Z","updated_at":"2026-01-15T00:01:21.965Z","avatar_url":"https://github.com/vtech6.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# goml\nNeural Networks from scratch in Go (standard library only)\n\n\u003cb\u003eLimitations: \u003c/b\u003e\n- No external libraries or modules\n- For simplicity, I limit the input shape to (1,x)\n\n\u003cb\u003eGoal: \u003c/b\u003e\n- Multilayer Perceptron (done)\n- Binary classification (done)\n- Support for multiple outputs (Multiple classification) (halted)\n- Visualization (in progress)\n\u003c/body\u003e\n\n\u003cb\u003eCurrent status:\u003c/b\u003e\n- Define basic data types (Input, Neuron, Layer)\n- Calculate neuron outputs [type: (1,x) array of weight*input+bias]\n- Define gradient methods and neural structure (heavily inspired by Karpathy's video)\n- Backpropagate and train for k steps\n- Produce and validate output\n- More activation functions (Sigmoid and ReLU)\n- Binary crossentropy\n\n\u003cb\u003e[Goml Visualizer](https://github.com/vtech6/goml-visualizer) (in progress): \u003c/b\u003e\u003cbr\u003e\u003cbr\u003e\n![goml-visualizer](https://github.com/vtech6/goml-visualizer/blob/main/testVisualizer.gif) \u003cbr\u003e\u003cbr\u003e\nThe Goml Visualizer was written using [Wails](https://wails.io) with React in Typescript for the frontend. The gif above shows the \u003cb\u003etest mode\u003c/b\u003e, which allows you to browse your test set and see which values were correctly predicted by the model.\u003cbr\u003e\u003cbr\u003e\n\u003cb\u003eReferences and inspiration:\u003c/b\u003e\n- [Sebastian Lauge's Neural Networks Video](https://www.youtube.com/watch?v=hfMk-kjRv4c)\n- [Andrej Karpathy's Micrograd Breakdown](https://www.youtube.com/watch?v=VMj-3S1tku0)\n- Aurelien Geron: Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (March 13, 2017, O'Reilly)\n\n\u003cb\u003eHow to run\u003c/b\u003e\n- Make sure you have a valid Go installation by running `go version`\n- Clone the repo\n- Run with `go run .`\n- The network parameters can be tweaked inside the `lib/network/run.go` file. Neuron activation functions can be found under `lib/network/neuron.go` and the engine blocks can be found under `lib/network/value.go`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvtech6%2Fgoml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvtech6%2Fgoml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvtech6%2Fgoml/lists"}