{"id":20131253,"url":"https://github.com/glassnotes/nn_qtomo","last_synced_at":"2026-05-13T03:08:57.892Z","repository":{"id":85604762,"uuid":"92863054","full_name":"glassnotes/NN_QTomo","owner":"glassnotes","description":"My playground for using neural networks to perform density matrix quantum tomography.","archived":false,"fork":false,"pushed_at":"2018-05-29T18:04:49.000Z","size":71002,"stargazers_count":2,"open_issues_count":3,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2026-02-01T08:41:31.982Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/glassnotes.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":"2017-05-30T18:20:47.000Z","updated_at":"2020-04-30T10:46:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"5d2ca77c-2c5e-4a8a-bc2c-b3501d460dd5","html_url":"https://github.com/glassnotes/NN_QTomo","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/glassnotes/NN_QTomo","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glassnotes%2FNN_QTomo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glassnotes%2FNN_QTomo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glassnotes%2FNN_QTomo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glassnotes%2FNN_QTomo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/glassnotes","download_url":"https://codeload.github.com/glassnotes/NN_QTomo/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/glassnotes%2FNN_QTomo/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32965874,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-12T23:30:32.555Z","status":"online","status_checked_at":"2026-05-13T02:00:07.132Z","response_time":115,"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":[],"created_at":"2024-11-13T20:47:08.628Z","updated_at":"2026-05-13T03:08:57.880Z","avatar_url":"https://github.com/glassnotes.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# NN_QTomo\n\nThe contents of this folder are an unpublished work in progress, beginning from summer 2017.\n\nContained are scripts, class files, and a set of running notes which detail\nhow to do density matrix tomography using a simple feed-forward neural network.\n\nWhile this technique work for the most part, it scales poorly with system dimension,\nand suffers from numerous problems, including state reconstructions that are not positive\nsemi-definite. Truly, it is a prime example of everything looking like a nail when\nyou have a large hammer, but it was a very helpful project in terms of learning\nabout neural networks and how to implement them in Python.\n\n## Requirements\n\n- numpy\n\n## Installation\n\nSimply run\n```\npython setup.py install\n```\nin the main directory.\n\n## Contents and usage\n\nYou can run this code as:\n```\npython nn_experiment.py \u003cparam_file.txt\u003e\n```\nThis executes a script which generates data for training a neural network (if no data file is available), trains it, and outputs the results either to a log file or to standard output. A sample parameter file is included in the main directory.\n\n\nThe relevant source files are as follows:\n\n`eigvecs.py` : Contains numpy arrays of the MUB vectors (eigenvectors of sets of disjoint\n             commuting operators) for various dimensions. Currently included are 2, 3, 4, 8, 32.\n\n\n`mcexperiment.py` : Monte Carlo simulation of measurement in some or all of the mutually\n                  unbiased bases.\n\n`nn_experiment.py` : Eats a parameter file and then generates data (if files not present), trains\n                   a neural network, and outputs results to a .log file.\n\n`running_notes.pdf` : A set of running notes and preliminary results.\n\n`sample_params.txt` : Example of a parameter file used by tomodatagenerator and tomoneuralnetwork\n                    to generate training data and then run the neural network tomography.\n\n`state_utils.py` : Helper functions for quantum state computations.\n\n`tomodatagenerator.py` : Using multiprocessing to generate Monte Carlo experiment data for a given\n                       parameter file. Outputs two CSV file containing the training data (input\n                       and output).\n\n`tomoneuralnetwork.py` : Builds and trains a neural network that trains using output files of\n                       tomodatagenerator.\n\nThanks to Roger Melko, Luis Sanchez-Soto, and Ulrich Seyfarth, on who I was able\nto bounce many ideas off of while working on this.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fglassnotes%2Fnn_qtomo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fglassnotes%2Fnn_qtomo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fglassnotes%2Fnn_qtomo/lists"}