{"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/sequential-neural-models-with-stochastic","title":"Sequential Neural Models with Stochastic Layers","arxiv_id":"1605.07571","date":"2016-05-24","proceeding":"NeurIPS 2016 12","authors":["Marco Fraccaro","Søren Kaae Sønderby","Ulrich Paquet","Ole Winther"],"abstract":"How can we efficiently propagate uncertainty in a latent state representation\nwith recurrent neural networks? This paper introduces stochastic recurrent\nneural networks which glue a deterministic recurrent neural network and a state\nspace model together to form a stochastic and sequential neural generative\nmodel. The clear separation of deterministic and stochastic layers allows a\nstructured variational inference network to track the factorization of the\nmodel's posterior distribution. By retaining both the nonlinear recursive\nstructure of a recurrent neural network and averaging over the uncertainty in a\nlatent path, like a state space model, we improve the state of the art results\non the Blizzard and TIMIT speech modeling data sets by a large margin, while\nachieving comparable performances to competing methods on polyphonic music\nmodeling.","url_abs":"http://arxiv.org/abs/1605.07571v2","url_pdf":"http://arxiv.org/pdf/1605.07571v2.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":"sequential-neural-models-with-stochastic","repo_url":"https://github.com/marcofraccaro/srnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"music-modeling","task_name":"Music Modeling"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.07571","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}