{"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/deep-temporal-sigmoid-belief-networks-for","title":"Deep Temporal Sigmoid Belief Networks for Sequence Modeling","arxiv_id":"1509.07087","date":"2015-09-23","proceeding":"NeurIPS 2015 12","authors":["Zhe Gan","Chunyuan Li","Ricardo Henao","David Carlson","Lawrence Carin"],"abstract":"Deep dynamic generative models are developed to learn sequential dependencies\nin time-series data. The multi-layered model is designed by constructing a\nhierarchy of temporal sigmoid belief networks (TSBNs), defined as a sequential\nstack of sigmoid belief networks (SBNs). Each SBN has a contextual hidden\nstate, inherited from the previous SBNs in the sequence, and is used to\nregulate its hidden bias. Scalable learning and inference algorithms are\nderived by introducing a recognition model that yields fast sampling from the\nvariational posterior. This recognition model is trained jointly with the\ngenerative model, by maximizing its variational lower bound on the\nlog-likelihood. Experimental results on bouncing balls, polyphonic music,\nmotion capture, and text streams show that the proposed approach achieves\nstate-of-the-art predictive performance, and has the capacity to synthesize\nvarious sequences.","url_abs":"http://arxiv.org/abs/1509.07087v1","url_pdf":"http://arxiv.org/pdf/1509.07087v1.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":"deep-temporal-sigmoid-belief-networks-for","repo_url":"https://github.com/zhegan27/TSBN_code_NIPS2015","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1509.07087","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}