{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1605.07571","atlas_url":"https://app.syntology.ai/?focus=1605.07571","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1605.07571"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1605.07571\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1605.07571"},"call":"get_concepts_for_paper(arxiv_id=\"1605.07571\")"}],"by_repo":[{"repo":"marcofraccaro/srnn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"f29ef479c49a163a2c89d5926dade1177248c6c23abb8aa1afddfd6f7c304a35","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}