{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-recurrent-latent-variable-model-for","title":"A Recurrent Latent Variable Model for Sequential Data","arxiv_id":"1506.02216","date":"2015-06-07","proceeding":"NeurIPS 2015 12","authors":["Junyoung Chung","Kyle Kastner","Laurent Dinh","Kratarth Goel","Aaron Courville","Yoshua Bengio"],"abstract":"In this paper, we explore the inclusion of latent random variables into the\ndynamic hidden state of a recurrent neural network (RNN) by combining elements\nof the variational autoencoder. We argue that through the use of high-level\nlatent random variables, the variational RNN (VRNN)1 can model the kind of\nvariability observed in highly structured sequential data such as natural\nspeech. We empirically evaluate the proposed model against related sequential\nmodels on four speech datasets and one handwriting dataset. Our results show\nthe important roles that latent random variables can play in the RNN dynamic\nhidden state.","url_abs":"http://arxiv.org/abs/1506.02216v6","url_pdf":"http://arxiv.org/pdf/1506.02216v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-recurrent-latent-variable-model-for","repo_url":"https://github.com/jych/nips2015_vrnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-recurrent-latent-variable-model-for","repo_url":"https://github.com/emited/VariationalRecurrentNeuralNetwork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-recurrent-latent-variable-model-for","repo_url":"https://github.com/joe5saia/PanelVariationalReccurentAutoEncoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"a-recurrent-latent-variable-model-for","repo_url":"https://github.com/mazrk7/discvae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-recurrent-latent-variable-model-for","repo_url":"https://github.com/dgedon/DeepSSM_SysID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1506.02216","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}