{"id":13790306,"url":"https://github.com/hunkim/deep_architecture_genealogy","last_synced_at":"2025-05-16T12:13:08.826Z","repository":{"id":93328860,"uuid":"109533627","full_name":"hunkim/deep_architecture_genealogy","owner":"hunkim","description":"Deep Learning Architecture  Genealogy Project","archived":false,"fork":false,"pushed_at":"2021-02-14T04:24:09.000Z","size":1467,"stargazers_count":1218,"open_issues_count":6,"forks_count":194,"subscribers_count":110,"default_branch":"master","last_synced_at":"2025-04-09T10:04:15.485Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://coggle.it/diagram/Wf5mYoJbsgABUF9P ","language":"Python","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/hunkim.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}},"created_at":"2017-11-04T22:04:20.000Z","updated_at":"2025-04-02T10:39:38.000Z","dependencies_parsed_at":"2023-03-04T09:30:44.805Z","dependency_job_id":null,"html_url":"https://github.com/hunkim/deep_architecture_genealogy","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/hunkim%2Fdeep_architecture_genealogy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hunkim%2Fdeep_architecture_genealogy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hunkim%2Fdeep_architecture_genealogy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hunkim%2Fdeep_architecture_genealogy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hunkim","download_url":"https://codeload.github.com/hunkim/deep_architecture_genealogy/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254527099,"owners_count":22085919,"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":"2024-08-03T22:00:41.089Z","updated_at":"2025-05-16T12:13:03.817Z","avatar_url":"https://github.com/hunkim.png","language":"Python","funding_links":[],"categories":["General","Python","Other useful related lists and resources"],"sub_categories":[],"readme":"# Deep Architecture Genealogy\nThere are so many new models and architectures. If you find something interesting and worth paying attention to, please send us a pull requests (PR) and write issues.\n`README.md` is automatically generated. Please send PRs on the `Neural Net Arch Genealogy.txt` file.\n## Mindmap Coggle Link\nhttps://coggle.it/diagram/Wf5mYoJbsgABUF9P\n![https://coggle.it/diagram/Wf5mYoJbsgABUF9P](Neural_Net_Arch_Genealogy.png)\n## Text Version\nThis is automatically generated. Please send a PR on the `Neural Net Arch Genealogy.txt` file.\n* Reinforcement Learning Algorithms\n  * [A3C, '16.02.06](https://arxiv.org/abs/1602.01783)\n  * [DARLA, '17.07.26](https://arxiv.org/pdf/1707.08475.pdf)\n  * [ACTKR, '17.08.17](https://arxiv.org/pdf/1708.05144.pdf)\n  * [c51, '17.10.27](https://arxiv.org/pdf/1710.10044.pdf)\n* CNN\n  * [AlexNet, '12.12](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)\n  * [VggNet, '14.09](https://arxiv.org/pdf/1409.1556.pdf)\n  * [GoogLeNet, '14.09](https://arxiv.org/abs/1409.4842)\n  * [ResNet, '15.12](https://arxiv.org/pdf/1512.03385v1.pdf)\n  * [DenseNet, '16.08](https://arxiv.org/pdf/1608.06993.pdf)\n  * [SENet: Squeeze-and-Excitation Networks, '17.09](https://arxiv.org/abs/1709.01507)\n  * Object Detection\n    * [R-CNN](https://arxiv.org/pdf/1311.2524.pdf)\n    * [Fast R-CNN](https://arxiv.org/pdf/1504.08083.pdf)\n    * [Faster R-CNN](https://arxiv.org/pdf/1506.01497.pdf)\n    * [Mask R-CNN](https://arxiv.org/pdf/1703.06870.pdf)\n    * [YOLO](https://arxiv.org/pdf/1506.02640.pdf)\n    * [SSD](https://arxiv.org/pdf/1512.02325.pdf)\n    * [R-FCN](https://arxiv.org/pdf/1605.06409.pdf)\n  * Semantic Segmentation\n    * [FCN](https://arxiv.org/pdf/1411.4038.pdf)\n    * [DeconvNet](https://arxiv.org/pdf/1505.04366.pdf)\n    * [DeepLab](https://arxiv.org/pdf/1606.00915.pdf)\n    * [U-Net](https://arxiv.org/pdf/1505.04597.pdf)\n  * Super-resolution\n    * [MemNet](https://arxiv.org/abs/1708.02209)\n    * [FSRCNN](https://arxiv.org/1608.00367)\n    * [SRCNN](https://arxiv.org/abs/1501.00092)\n    * [VDSR](https://arxiv.org/abs/1511.04587)\n    * [DRCN](https://arxiv.org/abs/1511.04491)\n    * [LabSRN](https://arxiv.org/abs/1704.03915)\n    * [EDSR](https://arxiv.org/abs/1707.02921)\n  * TTS\n    * [Wavenet, '16.09.12](https://arxiv.org/abs/1609.03499)\n* Generative Models\n  * Autoregressive models\n    * [MADE, '15.02.12](https://arxiv.org/pdf/1502.03509.pdf)\n    * [PixelRNN, '16.01.25](https://arxiv.org/pdf/1601.06759.pdf)\n    * [NADE, '16.05.07](https://arxiv.org/pdf/1605.02226.pdf)\n    * [PixelCNN, '16.06.16](https://arxiv.org/pdf/1606.05328.pdf)\n    * [PixelCNN++, '17.01.19](https://arxiv.org/pdf/1701.05517.pdf)\n  * Latent variable models\n    * [VAE, '13.12.20](https://arxiv.org/pdf/1312.6114.pdf)\n      * [CVAE, '14.06.20](https://arxiv.org/pdf/1406.5298.pdf)\n      * [AAE, '15.11.18](https://arxiv.org/pdf/1511.05644.pdf)\n      * [AVB, '17.01.17](https://arxiv.org/pdf/1701.04722.pdf)\n      * [VQ-VAE, '17.11.2](https://arxiv.org/abs/1711.00937)\n    * [GAN, '14.06.10](https://arxiv.org/pdf/1406.2661.pdf)\n      * Variants\n        * [CGAN, '14.11.06](https://arxiv.org/pdf/1411.1784.pdf)\n        * [DCGAN, '15.11.19](https://arxiv.org/pdf/1511.06434.pdf)\n        * [infoGAN, '16.06.12](https://arxiv.org/pdf/1704.00028.pdf)\n        * [EBGAN, '16.09.11](https://arxiv.org/pdf/1609.03126.pdf)\n        * [ACGAN, '16.10.30](https://arxiv.org/pdf/1610.09585.pdf)\n        * [WGAN, '17.01.26](https://arxiv.org/pdf/1701.07875.pdf)\n        * [BEGAN, '17.02.27](https://arxiv.org/pdf/1702.08431.pdf)\n        * [WGAN-GP, '17.03.31](https://arxiv.org/pdf/1704.00028.pdf)\n        * [TripleGAN, '17.03.07](https://arxiv.org/pdf/1703.02291.pdf)\n      * Applications\n        * [Pix2Pix, '16.11.21](https://arxiv.org/pdf/1611.07004v1.pdf)\n        * [PPGN, '16.11.30](https://arxiv.org/pdf/1612.00005.pdf)\n        * [StackGAN, '16.12.10](https://arxiv.org/pdf/1612.03242.pdf)\n* RNN\n  * [LSTM, '97.11](http://www.mitpressjournals.org/doi/10.1162/neco.1997.9.8.1735)\n  * [GRU, 14.11](https://arxiv.org/abs/1412.3555)\n  * [ACT: Adaptive Computation Time, '17.05](https://arxiv.org/abs/1603.08983)\n  * [S2S: RNN Encoder-Decoder, '14.06](https://arxiv.org/abs/1406.1078)\n    * [Attention: Jointly Learning to Align, '14.09](https://arxiv.org/abs/1409.0473)\n      * [Effective Approaches to Attention, Luong et al. '15.08](https://arxiv.org/abs/1508.04025)\n      * [DCN: Dynamic Coattention Networks, '16.08](https://arxiv.org/abs/1611.01604), [DCN+, '17.08](https://arxiv.org/abs/1711.00106)\n      * [Transformer: Attention Is All You Need, '17.06](https://arxiv.org/abs/1706.03762)\n* [Capsule Net, '17.10](https://arxiv.org/abs/1710.09829)\n* Memory Networks\n  * Neural Programming\n    * [Neural Turing Machine,'14.10](https://arxiv.org/pdf/1410.5401.pdf)\n    * [Neural Random-Access Machines,'16.02](https://arxiv.org/pdf/1511.06392.pdf)\n    * [Hierarchical Attentive Memory, '16.02](https://arxiv.org/abs/1602.03218)\n    * [Neural GPUs Learn Algorithms, '16.03](https://arxiv.org/pdf/1511.08228.pdf)\n    * [Neural Programmer,'16.08](https://arxiv.org/pdf/1511.04834.pdf)\n    * [Neural Module Networks, '16.06](https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Andreas_Neural_Module_Networks_CVPR_2016_paper.html)\n    * [Hybrid Computing, '16.10](https://www.nature.com/nature/journal/v538/n7626/full/nature20101.html)\n  * [Memory Networks,'14.10](https://arxiv.org/pdf/1410.3916.pdf)\n  * [End-to-End Memory Network,'15.03](https://arxiv.org/pdf/1503.08895.pdf)\n  * [DMN: Dynamic Memory Network, '16.03](https://arxiv.org/pdf/1506.07285.pdf), [DMN+, '16.04 ](https://arxiv.org/pdf/1603.01417.pdf) \n## Contributions\nYour pull requests and issues are always welcome.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhunkim%2Fdeep_architecture_genealogy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhunkim%2Fdeep_architecture_genealogy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhunkim%2Fdeep_architecture_genealogy/lists"}