{"id":21806849,"url":"https://github.com/roguh/hopfield_tests","last_synced_at":"2026-05-19T06:35:51.983Z","repository":{"id":89927893,"uuid":"47583268","full_name":"roguh/hopfield_tests","owner":"roguh","description":"These Python scripts can be used to test the recall effectiveness of Hopfield Networks. A sample dataset composed of the Walsh vectors, an orthogonal system is included by default.","archived":false,"fork":false,"pushed_at":"2015-12-07T23:45:27.000Z","size":7,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-26T04:42:06.188Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","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/roguh.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}},"created_at":"2015-12-07T22:28:47.000Z","updated_at":"2019-09-11T20:21:11.000Z","dependencies_parsed_at":"2023-03-16T03:31:59.265Z","dependency_job_id":null,"html_url":"https://github.com/roguh/hopfield_tests","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/roguh%2Fhopfield_tests","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/roguh%2Fhopfield_tests/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/roguh%2Fhopfield_tests/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/roguh%2Fhopfield_tests/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/roguh","download_url":"https://codeload.github.com/roguh/hopfield_tests/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244759961,"owners_count":20505716,"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":[],"created_at":"2024-11-27T12:30:31.553Z","updated_at":"2026-05-19T06:35:46.963Z","avatar_url":"https://github.com/roguh.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"Hopfield Network Performance Tests\n==================================\n\nHopfield Networks are recursive neural networks that function as content-addressable memory. Although commonly referenced for their clear theory, it is best to see the bibliography for that. Instead, the programs here can be used to test the recall effectiveness of Hopfield Networks. A sample dataset composed of the Walsh vectors, an orthogonal system is included by default.\n\nHow to install\n--------------\nPython, numpy, matplotlib/pyplot are needed.\nSee [here](http://matplotlib.org/users/installing.html) for a description of the process.\n\nHow to run\n----------\n\n```\npython3 tests.py --nvectors --size --samples --latex-ouput\n```\n\nSample Results\n--------------\n```\npython3 tests.py --nvectors 3, 5, 10 --samples 100 --size 5\n\nvector size 5, vectors in memory 3 ---  randomly flipped 0% of bits\n\tmatched, nearly matched, mean iterations to convergence\n\t(100.00 ±   0.00)%, (100.00 ±   0.00)% -- 1.00\n\n  5,   3 ---  0.1%\n\t(100.00 ±   0.00)%, (100.00 ±   0.00)% -- 2.00\n\n  5,   3 ---  0.2%\n\t( 70.00 ±  20.00)%, ( 95.62 ±  14.79)% -- 2.00\n\n  5,   5 ---  0.0%\n\t(100.00 ±   0.00)%, (100.00 ±   0.00)% -- 1.00\n\n  5,   5 ---  0.1%\n\t(100.00 ±   0.00)%, (100.00 ±   0.00)% -- 2.00\n\n  5,   5 ---  0.2%\n\t( 50.00 ±  20.98)%, ( 92.50 ±  20.16)% -- 2.67\n\n  5,  10 ---  0.0%\n\t(100.00 ±   0.00)%, (100.00 ±   0.00)% -- 1.00\n\n  5,  10 ---  0.1%\n\t( 47.27 ±  16.18)%, ( 96.70 ±  11.00)% -- 1.47\n\n  5,  10 ---  0.2%\n\t(  1.82 ±   6.03)%, ( 79.72 ±  20.75)% -- 1.84\n```\n\nBibliography\n------------\n[The Hopfield Model](http://page.mi.fu-berlin.de/rojas/neural/chapter/K13.pdf)\n[Hopfield Networks](http://www.comp.leeds.ac.uk/ai23/reading/Hopfield.pdf)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Froguh%2Fhopfield_tests","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Froguh%2Fhopfield_tests","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Froguh%2Fhopfield_tests/lists"}