{"id":18028522,"url":"https://github.com/interactivetech/bayesiancnn-sghmc","last_synced_at":"2025-03-27T03:30:49.138Z","repository":{"id":74751955,"uuid":"113942446","full_name":"interactivetech/BayesianCNN-SGHMC","owner":"interactivetech","description":"This is our code repository for our Final Project for ORIE 6741 Bayesian Machine Learning Class. ","archived":false,"fork":false,"pushed_at":"2020-06-18T01:01:49.000Z","size":12282,"stargazers_count":9,"open_issues_count":0,"forks_count":1,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-03-22T23:25:12.356Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/interactivetech.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2017-12-12T04:15:38.000Z","updated_at":"2023-09-23T12:37:10.000Z","dependencies_parsed_at":"2023-05-19T03:45:11.238Z","dependency_job_id":null,"html_url":"https://github.com/interactivetech/BayesianCNN-SGHMC","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/interactivetech%2FBayesianCNN-SGHMC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/interactivetech%2FBayesianCNN-SGHMC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/interactivetech%2FBayesianCNN-SGHMC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/interactivetech%2FBayesianCNN-SGHMC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/interactivetech","download_url":"https://codeload.github.com/interactivetech/BayesianCNN-SGHMC/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245778339,"owners_count":20670682,"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":"2024-10-30T08:42:25.768Z","updated_at":"2025-03-27T03:30:49.133Z","avatar_url":"https://github.com/interactivetech.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# A Bayesian framework for Convolutional Neural Networks using Stochastic Gradient Hamiltonian Monte Carlo\n\nThis project we formulate a Bayesian framework for Convolutional Neural Networks using Stochastic Gradient Hamiltonian Monte Carlo(SGHMC)\n\n\n\nLink to report here: [link](https://s3.amazonaws.com/andrewmendez.me/files/+Bayesian+Convolutional+Neural+Networks+using+Stochastic+Gradient+Hamiltonian+Monte+Carlo.pdf)\n\nThis repository implements a Bayesian CNN framework using SGHMC. We compare our method to MC-Dropout. Experiments and models were developed using Tensorflow and Edward. \n\nAbstract:\n\nConvolutional Neural Networks(CNN's) are powerful image processing models that have no estimates of uncertainty. (Gal \u0026 Ghahramani, 2015) developed efficient estimation of CNN's weight uncertainty using variational approximation. Although this method is promising, variational approximation is known to underestimate the true distribution and does not fit well on multi-modal distributions (Gal \u0026 Ghahramani, 2015). The purpose of this study is to explore better inference methods, such as Stochastic Gradient Hamiltonian Monte Carlo, to better approximate model posterior of Convolutional Neural Networks architectures and improve class label prediction.\n\n#ToDo\n\n1. Conducting model criticism by analyzing the posterior predictive distribution. Tutorial here: http://edwardlib.org/tutorials/criticism\n\nOne check would be a PPC: Posterior predictive checks (PPCs) analyze the degree to which data generated from the model deviate from data generated from the true distribution. \n\nFor more interesting links of probabalistic inference:\nLook at the Edward Library:http://edwardlib.org/\nBayesian Method for Hackers: https://github.com/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finteractivetech%2Fbayesiancnn-sghmc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finteractivetech%2Fbayesiancnn-sghmc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finteractivetech%2Fbayesiancnn-sghmc/lists"}