{"id":15601024,"url":"https://github.com/lucidrains/esbn-pytorch","last_synced_at":"2025-05-05T15:51:18.607Z","repository":{"id":57426901,"uuid":"326064888","full_name":"lucidrains/ESBN-pytorch","owner":"lucidrains","description":"Usable implementation of Emerging Symbol Binding Network (ESBN), in Pytorch","archived":false,"fork":false,"pushed_at":"2021-01-06T00:37:20.000Z","size":66,"stargazers_count":24,"open_issues_count":0,"forks_count":3,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-28T12:52:18.911Z","etag":null,"topics":["abstract-reasoning","artificial-intelligence","deep-learning","memory","neuro-symbolic-learning"],"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/lucidrains.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":"2021-01-01T22:16:08.000Z","updated_at":"2025-02-04T23:52:43.000Z","dependencies_parsed_at":"2022-09-13T15:22:46.801Z","dependency_job_id":null,"html_url":"https://github.com/lucidrains/ESBN-pytorch","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2FESBN-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2FESBN-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2FESBN-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2FESBN-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/ESBN-pytorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252526589,"owners_count":21762535,"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","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":["abstract-reasoning","artificial-intelligence","deep-learning","memory","neuro-symbolic-learning"],"created_at":"2024-10-03T02:12:26.028Z","updated_at":"2025-05-05T15:51:18.581Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"./esbn.png\" width=\"600px\"\u003e\u003c/img\u003e\n\n## Emerging Symbol Binding Network (ESBN) - Pytorch\n\nUsable implementation of \u003ca href=\"https://openreview.net/forum?id=LSFCEb3GYU7\"\u003eEmerging Symbol Binding Network\u003c/a\u003e (ESBN), in Pytorch. They propose to have the main recurrent neural network interact with the input image representations only through a set of memory key / values.\n\nThe input image representation are cast as memory values, and are explicitly bound to memory keys that are generated by the network. The network generates the memory keys after getting a sum of all previous memory keys weighted by the similarity of the incoming representation to the set of memory values in storage.\n\nThis decoupling / indirection of sensory to abstract processing allows the network to outperform all previous approaches, including transformers.\n\n## Usage\n\n```python\nimport torch\nfrom esbn_pytorch import ESBN\n\nmodel = ESBN(\n    value_dim = 64,\n    key_dim = 64,\n    hidden_dim = 512,\n    output_dim = 4\n)\n\nimages = torch.randn(3, 2, 3, 32, 32) # (n, b, c, h, w)\nmodel(images) # (3, 2, 4) # (n, b, o)\n```\n\n## Citations\n\n```bibtex\n@misc{webb2020emergent,\n    title={Emergent Symbols through Binding in External Memory}, \n    author={Taylor W. Webb and Ishan Sinha and Jonathan D. Cohen},\n    year={2020},\n    eprint={2012.14601},\n    archivePrefix={arXiv},\n    primaryClass={cs.AI}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fesbn-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Fesbn-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fesbn-pytorch/lists"}