{"id":37101707,"url":"https://github.com/nytopop/gohtm","last_synced_at":"2026-01-14T12:20:46.026Z","repository":{"id":57531544,"uuid":"73041418","full_name":"nytopop/gohtm","owner":"nytopop","description":"An implementation of the HTM machine learning algorithm.","archived":false,"fork":false,"pushed_at":"2017-04-17T22:53:44.000Z","size":1917,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-06-20T17:33:15.749Z","etag":null,"topics":["golang","htm","machine-learning","unsupervised-learning"],"latest_commit_sha":null,"homepage":null,"language":"Go","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/nytopop.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":"2016-11-07T04:10:45.000Z","updated_at":"2021-12-22T08:22:32.000Z","dependencies_parsed_at":"2022-09-06T23:10:58.761Z","dependency_job_id":null,"html_url":"https://github.com/nytopop/gohtm","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nytopop/gohtm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nytopop%2Fgohtm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nytopop%2Fgohtm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nytopop%2Fgohtm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nytopop%2Fgohtm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nytopop","download_url":"https://codeload.github.com/nytopop/gohtm/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nytopop%2Fgohtm/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28420408,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T10:47:48.104Z","status":"ssl_error","status_checked_at":"2026-01-14T10:46:19.031Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: 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":["golang","htm","machine-learning","unsupervised-learning"],"created_at":"2026-01-14T12:20:45.127Z","updated_at":"2026-01-14T12:20:45.974Z","avatar_url":"https://github.com/nytopop.png","language":"Go","funding_links":[],"categories":[],"sub_categories":[],"readme":"# go-htm \n[![GoDoc](https://godoc.org/github.com/nytopop/gohtm?status.svg)](https://godoc.org/github.com/nytopop/gohtm) [![Build Status](https://travis-ci.org/nytopop/gohtm.svg?branch=master)](https://travis-ci.org/nytopop/gohtm)\n\nAn implementation of the HTM algorithm.\n\nIn progress.\n\n## Overview\n\nHTM (Hierarchical Temporal Memory) is an online, unsupervised learning algorithm pioneered by the folks over at [Numenta](http://numenta.org/). This is not an up to spec implementation; gohtm diverges somewhat from the original.\n\nMy goals for this project are geared more towards experimentation and generalized machine intelligence development, rather than anomaly detection and vector prediction. I'm experimenting with some different approaches toward the storage and manipulation of synaptic connectivity networks, primarily to the ultimate goal of efficient scaling across multiple machines with large(r) networks of HTM regions, as well as coordination amongst them.\n\nFurther, I'm devoting attention to vision oriented problems and coordination of full multi-sensory modalities into global ensemble representations.\n\n## Roadmap\n\n- [x] Encoder Base\n- [x] Scalar encoder\n- [ ] Audio encoder\n- [ ] Vision encoder\n- [x] Random distributed scalar encoder\n- [x] Spatial Pooler\n- [x] Temporal Memory\n- [ ] Temporal Pooler\n- [ ] Classifier\n- [ ] Tests\n- [ ] Visualization\n\n## Experiments \u0026 research directions\n### Networks\n- [ ] Spec out a network definition language. Code generation? \n- [ ] First in Last out stack for processing\n\n### Spatial Pooler\n- [ ] Needs fixing, probably a rewrite of the whole thing\n- [ ] Make tests to verify proper behavior of pooling\n\n\tbit distribution, randomness, uniformity, etc\n\n### Temporal memory\n- [ ] get some benchmark sequences for testing prediction accuracy, etc\n- [ ] figure out what to do when we hit the limit on cellular objects. More recent data is preferable, online learning and all...\n- [ ] fix the anomaly calculation\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnytopop%2Fgohtm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnytopop%2Fgohtm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnytopop%2Fgohtm/lists"}