{"id":18261663,"url":"https://github.com/timudk/gmin","last_synced_at":"2025-04-09T00:37:22.607Z","repository":{"id":91804001,"uuid":"203398089","full_name":"timudk/GMiN","owner":"timudk","description":"Jupyter notebooks for generative models using NumPy","archived":false,"fork":false,"pushed_at":"2019-09-04T13:05:08.000Z","size":177,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-02-14T18:53:15.668Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/timudk.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":"2019-08-20T14:55:27.000Z","updated_at":"2024-08-03T16:33:22.000Z","dependencies_parsed_at":null,"dependency_job_id":"0ffc1cce-f954-4798-925f-64dc1dd7be37","html_url":"https://github.com/timudk/GMiN","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/timudk%2FGMiN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timudk%2FGMiN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timudk%2FGMiN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/timudk%2FGMiN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/timudk","download_url":"https://codeload.github.com/timudk/GMiN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247952713,"owners_count":21023942,"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":"2024-11-05T11:04:36.909Z","updated_at":"2025-04-09T00:37:22.590Z","avatar_url":"https://github.com/timudk.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Generative models in NumPy\n\nThis repository contains implementations of generative models using NumPy.\n\n## Available implementations\n1. Naive Bayes (classifier)\n2. Boltzmann machine\n3. Restricted Boltzmann machine\n\n## In progress\n1. GAN\n\n## Motivation\nIn my opinion, the best way to grasp a new generative model is by implementing it in NumPy. Only by doing so, one can understand the full picture of (probabilisitc) model assumptions, optimization and sampling. \n\n## Sources of inspiration\n1. [Danilo Rezende's slides on deep generative models](https://docs.google.com/presentation/d/e/2PACX-1vSwRVxRHDarUx2mwXrsrlrtdTVTyEiFkWjJ9TvJ5ad6gbB3PDZSgD9yHAUiB6DcO1zP7LXBpxzc0SzC/pub?start=true\u0026loop=true\u0026delayms=10000\u0026slide=id.gd9c453428_0_16)\n2. Papers on generative models:\n  * Introducing GANs: [http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf](http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf)\n  * Introducing Variational autoencoders: [Auto-Encoding Variational Bayes](https://arxiv.org/pdf/1312.6114.pdf)\n  * [A Practical Guide to Training Restricted Boltzmann Machines](https://www.cs.toronto.edu/~hinton/absps/guideTR.pdf)\n  * [Stochastic Backpropagation and Approximate Inferencein Deep Generative Models](https://arxiv.org/pdf/1401.4082.pdf)\n  * Introducing normalizing flows: [Variational Inference with Normalizing Flows](https://arxiv.org/pdf/1505.05770.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimudk%2Fgmin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftimudk%2Fgmin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftimudk%2Fgmin/lists"}