@inproceedings{
 title = {DRAW: A Recurrent Neural Network For Image Generation},
 type = {inproceedings},
 year = {2015},
 pages = {1462-1471},
 websites = {https://proceedings.mlr.press/v37/gregor15.html},
 month = {6},
 publisher = {PMLR},
 id = {3f92f8d4-7878-33fa-bf1e-cf8aeaf9229a},
 created = {2022-03-28T09:45:00.921Z},
 accessed = {2022-03-26},
 file_attached = {true},
 profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
 group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
 last_modified = {2022-03-29T08:01:20.353Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {gregorDRAWRecurrentNeural2015},
 source_type = {inproceedings},
 short_title = {DRAW},
 notes = {ISSN: 1938-7228},
 private_publication = {false},
 abstract = {This paper introduces the Deep Recurrent Attentive Writer (DRAW) architecture for image generation with neural networks. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it is able to generate images that are indistinguishable from real data with the naked eye.},
 bibtype = {inproceedings},
 author = {Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo and Wierstra, Daan},
 booktitle = {Proceedings of the 32nd International Conference on Machine Learning}
}

{"_id":"mBP7NSpkf2aWcsCh7","bibbaseid":"gregor-danihelka-graves-rezende-wierstra-drawarecurrentneuralnetworkforimagegeneration-2015","author_short":["Gregor, K.","Danihelka, I.","Graves, A.","Rezende, D.","Wierstra, D."],"bibdata":{"title":"DRAW: A Recurrent Neural Network For Image Generation","type":"inproceedings","year":"2015","pages":"1462-1471","websites":"https://proceedings.mlr.press/v37/gregor15.html","month":"6","publisher":"PMLR","id":"3f92f8d4-7878-33fa-bf1e-cf8aeaf9229a","created":"2022-03-28T09:45:00.921Z","accessed":"2022-03-26","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-03-29T08:01:20.353Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"gregorDRAWRecurrentNeural2015","source_type":"inproceedings","short_title":"DRAW","notes":"ISSN: 1938-7228","private_publication":false,"abstract":"This paper introduces the Deep Recurrent Attentive Writer (DRAW) architecture for image generation with neural networks. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it is able to generate images that are indistinguishable from real data with the naked eye.","bibtype":"inproceedings","author":"Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo and Wierstra, Daan","booktitle":"Proceedings of the 32nd International Conference on Machine Learning","bibtex":"@inproceedings{\n title = {DRAW: A Recurrent Neural Network For Image Generation},\n type = {inproceedings},\n year = {2015},\n pages = {1462-1471},\n websites = {https://proceedings.mlr.press/v37/gregor15.html},\n month = {6},\n publisher = {PMLR},\n id = {3f92f8d4-7878-33fa-bf1e-cf8aeaf9229a},\n created = {2022-03-28T09:45:00.921Z},\n accessed = {2022-03-26},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-03-29T08:01:20.353Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {gregorDRAWRecurrentNeural2015},\n source_type = {inproceedings},\n short_title = {DRAW},\n notes = {ISSN: 1938-7228},\n private_publication = {false},\n abstract = {This paper introduces the Deep Recurrent Attentive Writer (DRAW) architecture for image generation with neural networks. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it is able to generate images that are indistinguishable from real data with the naked eye.},\n bibtype = {inproceedings},\n author = {Gregor, Karol and Danihelka, Ivo and Graves, Alex and Rezende, Danilo and Wierstra, Daan},\n booktitle = {Proceedings of the 32nd International Conference on Machine Learning}\n}","author_short":["Gregor, K.","Danihelka, I.","Graves, A.","Rezende, D.","Wierstra, D."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/348c5a65-6cb9-ab93-547c-d0251319a6c6/Gregor_et_al___2015___DRAW_A_Recurrent_Neural_Network_For_Image_Generat.pdf.pdf","Website":"https://proceedings.mlr.press/v37/gregor15.html"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"gregor-danihelka-graves-rezende-wierstra-drawarecurrentneuralnetworkforimagegeneration-2015","role":"author","metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["CmHEoydhafhbkXXt5","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["draw","recurrent","neural","network","image","generation","gregor","danihelka","graves","rezende","wierstra"],"title":"DRAW: A Recurrent Neural Network For Image Generation","year":2015}