{"id":22057237,"url":"https://github.com/lgaspard/brc","last_synced_at":"2026-05-01T01:32:25.998Z","repository":{"id":112680477,"uuid":"386966886","full_name":"lgaspard/brc","owner":"lgaspard","description":"PyTorch implementation of the bistable recurrent cell (BRC) and recurrently neuromodulated bistable recurrent cell (nBRC)","archived":false,"fork":false,"pushed_at":"2021-08-06T14:57:10.000Z","size":6,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-23T16:29:29.830Z","etag":null,"topics":["bistability","bistable-recurrent-cell","brc","pytorch","pytorch-implementation","recurrent-neural-network","rnn"],"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/lgaspard.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":"2021-07-17T14:58:24.000Z","updated_at":"2021-08-21T09:42:57.000Z","dependencies_parsed_at":"2023-09-11T09:45:35.791Z","dependency_job_id":null,"html_url":"https://github.com/lgaspard/brc","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/lgaspard/brc","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lgaspard%2Fbrc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lgaspard%2Fbrc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lgaspard%2Fbrc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lgaspard%2Fbrc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lgaspard","download_url":"https://codeload.github.com/lgaspard/brc/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lgaspard%2Fbrc/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32482460,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-30T13:12:12.517Z","status":"ssl_error","status_checked_at":"2026-04-30T13:12:06.837Z","response_time":57,"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":["bistability","bistable-recurrent-cell","brc","pytorch","pytorch-implementation","recurrent-neural-network","rnn"],"created_at":"2024-11-30T16:17:19.930Z","updated_at":"2026-05-01T01:32:25.949Z","avatar_url":"https://github.com/lgaspard.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PyTorch Implementation of (n)BRC\n\nPyTorch implementation of the bistable recurrent cell (BRC) and recurrently\nneuromodulated bistable recurrent cell (nBRC).\n\nThe available classes, `BRCLayer`, `nBRCLayer`, `BRC` and `nBRC`, are\ndocumented in [brc.py](brc.py).\n\n## Download\n\n```\ngit clone https://github.com/lgaspard/brc\ncd brc/\n```\n\n## Example usage\n\nSee [main.py](main.py) for a *copy-first-input* benchmark with the BRC cell.\n```\npython3 main.py\n```\n\n## Notes\n\nThe implementation is similar to that of `torch.nn.GRU`, such that the output\nof the RNN is its hidden state.  A small wrapper is proposed in\n[main.py](main.py) to add a linear layer on top of the recurrent cell.\n\nAlso note that the parameter `train_h0` allows to make the initial hidden state\na trainable parameter of the recurrent cell.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flgaspard%2Fbrc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flgaspard%2Fbrc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flgaspard%2Fbrc/lists"}