{"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-generative-networks-for-sequence","title":"Deep Generative Networks For Sequence Prediction","arxiv_id":"1804.06546","date":"2018-04-18","proceeding":null,"authors":["Markus Beissinger"],"abstract":"This thesis investigates unsupervised time series representation learning for\nsequence prediction problems, i.e. generating nice-looking input samples given\na previous history, for high dimensional input sequences by decoupling the\nstatic input representation from the recurrent sequence representation. We\nintroduce three models based on Generative Stochastic Networks (GSN) for\nunsupervised sequence learning and prediction. Experimental results for these\nthree models are presented on pixels of sequential handwritten digit (MNIST)\ndata, videos of low-resolution bouncing balls, and motion capture data. The\nmain contribution of this thesis is to provide evidence that GSNs are a viable\nframework to learn useful representations of complex sequential input data, and\nto suggest a new framework for deep generative models to learn complex\nsequences by decoupling static input representations from dynamic time\ndependency representations.","url_abs":"http://arxiv.org/abs/1804.06546v1","url_pdf":"http://arxiv.org/pdf/1804.06546v1.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-generative-networks-for-sequence","repo_url":"https://github.com/mbeissinger/recurrent_gsn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"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":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}