{"id":20508787,"url":"https://github.com/s3gmentati0nfaultuni/autoencoders","last_synced_at":"2025-08-09T09:17:16.319Z","repository":{"id":214205813,"uuid":"735955963","full_name":"S3gmentati0nFaultUni/autoencoders","owner":"S3gmentati0nFaultUni","description":"Autoencoders implementation for the 8th sheet of the course of Machine Learning and Physics at Heidelberg University","archived":false,"fork":false,"pushed_at":"2024-07-30T17:49:58.000Z","size":6288,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-16T08:26:55.509Z","etag":null,"topics":["autoencoder","machine-learning","notebook-jupyter","project"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/S3gmentati0nFaultUni.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":"2023-12-26T15:08:18.000Z","updated_at":"2024-08-25T21:59:48.000Z","dependencies_parsed_at":"2024-07-30T21:25:23.684Z","dependency_job_id":"3692ddf0-6683-43ad-b7a4-528ad2d5a1c2","html_url":"https://github.com/S3gmentati0nFaultUni/autoencoders","commit_stats":null,"previous_names":["s3gmentati0nfault/autoencoders","s3gmentati0nfaultuni/autoencoders"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S3gmentati0nFaultUni%2Fautoencoders","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S3gmentati0nFaultUni%2Fautoencoders/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S3gmentati0nFaultUni%2Fautoencoders/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/S3gmentati0nFaultUni%2Fautoencoders/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/S3gmentati0nFaultUni","download_url":"https://codeload.github.com/S3gmentati0nFaultUni/autoencoders/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242111756,"owners_count":20073478,"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":["autoencoder","machine-learning","notebook-jupyter","project"],"created_at":"2024-11-15T20:20:25.242Z","updated_at":"2025-03-05T22:20:05.238Z","avatar_url":"https://github.com/S3gmentati0nFaultUni.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Autoencoders\n## What about it\nIn this small project (bonus exercise sheet for the course of Machine Learning and Physics) the objective was to build an autoencoder using various two different sub-architectures, the first one being MLPs and the second one being CNNs. As a dataset we got a set of jet pictures from professot Tilman Plehn and we had to come up with a series of observations on how the two architectures that we came up with were able to reconstruct the images that were given as inputs.\n\n## Work in progress\nI still want to put some effort in this project, even though the due date is already over, because I want to understand a couple of things that didn't really sit right with me, here is an approximative roadmap of the process:\n\n- [ ] Clean the code and make it easier to understand\n- [x] Understand why the CNN has lower accuracy than the MLP substructure\n    I found a way to make sure that the CNN has higher accuracy than the MLP substructure but it\n    takes 5 times to run and the ROC curve is kind of a weird result.\n- [ ] Make the Convolutional Neural Network more efficient.\n\n## Quality of the solution\nEven though our solution was not totally complete it was deemed close to perfect, thus it's possible for anyone to see it as a tutorial that is very close to beginner level (bragging, but still down to earth).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fs3gmentati0nfaultuni%2Fautoencoders","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fs3gmentati0nfaultuni%2Fautoencoders","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fs3gmentati0nfaultuni%2Fautoencoders/lists"}