{"id":22239704,"url":"https://github.com/mariamagro/exploring_variational_autoencoders_gaussian_mixture_models","last_synced_at":"2025-03-25T10:15:50.162Z","repository":{"id":253701117,"uuid":"844259283","full_name":"mariamagro/Exploring_Variational_Autoencoders_Gaussian_Mixture_Models","owner":"mariamagro","description":"This project investigates Variational Autoencoders (VAEs) for generating synthetic data from a 3D Gaussian Mixture Model (GMM). It covers data synthesis, VAE architecture with dense layers, and model evaluation, including clustering and T-SNE visualization to assess the VAE's performance and latent space representation.","archived":false,"fork":false,"pushed_at":"2024-08-18T21:29:55.000Z","size":4715,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-30T09:23:17.183Z","etag":null,"topics":["gmm","vae-pytorch"],"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/mariamagro.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":"2024-08-18T21:18:38.000Z","updated_at":"2024-08-18T21:29:58.000Z","dependencies_parsed_at":"2024-08-18T22:44:26.290Z","dependency_job_id":null,"html_url":"https://github.com/mariamagro/Exploring_Variational_Autoencoders_Gaussian_Mixture_Models","commit_stats":null,"previous_names":["mariamagro/exploring_variational_autoencoders_gaussian_mixture_models"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamagro%2FExploring_Variational_Autoencoders_Gaussian_Mixture_Models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamagro%2FExploring_Variational_Autoencoders_Gaussian_Mixture_Models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamagro%2FExploring_Variational_Autoencoders_Gaussian_Mixture_Models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mariamagro%2FExploring_Variational_Autoencoders_Gaussian_Mixture_Models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mariamagro","download_url":"https://codeload.github.com/mariamagro/Exploring_Variational_Autoencoders_Gaussian_Mixture_Models/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245440575,"owners_count":20615633,"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":["gmm","vae-pytorch"],"created_at":"2024-12-03T03:21:05.594Z","updated_at":"2025-03-25T10:15:49.961Z","avatar_url":"https://github.com/mariamagro.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural Networks: Exploring Variational Autoencoders with Gaussian Mixture Models\n\n**Credit:**\nThe implementation is based on tasks provided by Pablo M. Olmos.\n\n**Completed by:**\n- **María Ángeles Magro Garrote** - [mariamagro](https://github.com/mariamagro)\n- **Marina Gómez Rey** - [MarinaGRey](https://github.com/MarinaGRey)\n- **Ángela Durán**\n\n## Overview\n\nThis project explores the application of Variational Autoencoders (VAEs) in the context of generating synthetic data from a 3-dimensional Gaussian Mixture Model (GMM). Our aim is to evaluate the VAE's capability to capture the intricate structure of multi-modal distributions and produce samples that closely emulate the ground truth distribution.\n\nThe project consists of the following components:\n- **Synthetic Data Generation**: We use a Gaussian Mixture Model (GMM) to create a synthetic dataset for training and evaluating the VAE.\n- **VAE Architecture**: We construct and train a VAE using dense layers, and analyze its performance in capturing and reconstructing the data.\n- **Clustering and Mode Identification**: We use clustering techniques and mode identification to analyze the VAE's latent space and compare it with the ground truth data.\n- **T-SNE Visualization**: We visualize the latent space representations using T-SNE to gain insights into the VAE's performance and the structure of the data.\n\n## Contents\n\n- `report.pdf`: A comprehensive report detailing the project, including methodology, results, and insights.\n- `part1.ipynb`: Jupyter Notebook containing the implementation of synthetic data generation and VAE model definition.\n- `part2.ipynb`: Jupyter Notebook for training the VAE, generating samples, performing clustering, mode identification, and T-SNE visualization.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmariamagro%2Fexploring_variational_autoencoders_gaussian_mixture_models","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmariamagro%2Fexploring_variational_autoencoders_gaussian_mixture_models","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmariamagro%2Fexploring_variational_autoencoders_gaussian_mixture_models/lists"}