{"id":21280643,"url":"https://github.com/borgwardtlab/neural-persistence","last_synced_at":"2025-08-16T21:11:41.312Z","repository":{"id":69144796,"uuid":"171832789","full_name":"BorgwardtLab/Neural-Persistence","owner":"BorgwardtLab","description":"Code for the paper 'Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology'","archived":false,"fork":false,"pushed_at":"2019-02-25T15:37:51.000Z","size":13,"stargazers_count":31,"open_issues_count":0,"forks_count":8,"subscribers_count":10,"default_branch":"master","last_synced_at":"2025-07-11T11:54:38.757Z","etag":null,"topics":["algebraic-topology","deep-learning","iclr","iclr2019","machine-learning","neural-networks","persistent-homology"],"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/BorgwardtLab.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":"2019-02-21T08:38:13.000Z","updated_at":"2025-03-24T17:24:20.000Z","dependencies_parsed_at":"2023-03-06T08:45:16.580Z","dependency_job_id":null,"html_url":"https://github.com/BorgwardtLab/Neural-Persistence","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BorgwardtLab/Neural-Persistence","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2FNeural-Persistence","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2FNeural-Persistence/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2FNeural-Persistence/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2FNeural-Persistence/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BorgwardtLab","download_url":"https://codeload.github.com/BorgwardtLab/Neural-Persistence/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BorgwardtLab%2FNeural-Persistence/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":270771222,"owners_count":24642282,"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","status":"online","status_checked_at":"2025-08-16T02:00:11.002Z","response_time":91,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["algebraic-topology","deep-learning","iclr","iclr2019","machine-learning","neural-networks","persistent-homology"],"created_at":"2024-11-21T10:37:55.209Z","updated_at":"2025-08-16T21:11:41.293Z","avatar_url":"https://github.com/BorgwardtLab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology \n\nThis repository contains the code for our paper [*Neural Persistence:\nA Complexity Measure for Deep Neural Networks Using Algebraic\nTopology*](https://openreview.net/pdf?id=ByxkijC5FQ),\nwhich was published as an ICLR 2019 conference paper.\n\nThis repository is a work in progress. We aim to add more experiments\nover time.\n\n# Deep learning best practices in light of neural persistence \n\nThis repository can be used to reproduce the experiment from Section 4.1\nof the publication. To ensure ease of use and reproducibility, it relies\non Docker.\n\nTo install Docker, please follow the [official manual](https://www.docker.com/get-started).\nHaving set up Docker for your operating system, the subsequent sections\nguide you through the process.\n\n## Build docker container\n\n```bash\ncd $REPODIR\ndocker build -t neuralpersistence .\n```\n\n## Run experiments and summarize results\n\n```bash\ndocker run -v $PWD/results/:/Neuralpersistence/results/ neuralpersistence python3 -u run_experiments.py\ndocker run -v $PWD/results/:/Neuralpersistence/results/ neuralpersistence python3 combine_runs.py results/runs/* --output results/combined_runs.csv\n```\n\n## Plot the results\n\n```bash\ndocker run -v $PWD/results/:/Neuralpersistence/results/ neuralpersistence python3 create_plots.py results/combined_runs.csv results/combined_runs.pdf\n```\n\nThe visualizations of the mean normalized neural persistence, as well as\nthe test accuracy can be found in `results/combined_runs.pdf`.\n\n# Citation\n\nPlease use the following citation to refer to this paper:\n\n    @inproceedings{Rieck19a,\n      title     = {Neural Persistence: {A} Complexity Measure for Deep Neural Networks Using Algebraic Topology},\n      author    = {Bastian Rieck and Matteo Togninalli and Christian Bock and Michael Moor and Max Horn and Thomas Gumbsch and Karsten Borgwardt},\n      booktitle = {International Conference on Learning Representations~(ICLR)},\n      year      = {2019},\n      url       = {https://openreview.net/forum?id=ByxkijC5FQ},\n    }\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborgwardtlab%2Fneural-persistence","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fborgwardtlab%2Fneural-persistence","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fborgwardtlab%2Fneural-persistence/lists"}