{"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/stcn-stochastic-temporal-convolutional","title":"STCN: Stochastic Temporal Convolutional Networks","arxiv_id":"1902.06568","date":"2019-02-18","proceeding":"ICLR 2019 5","authors":["Emre Aksan","Otmar Hilliges"],"abstract":"Convolutional architectures have recently been shown to be competitive on\nmany sequence modelling tasks when compared to the de-facto standard of\nrecurrent neural networks (RNNs), while providing computational and modeling\nadvantages due to inherent parallelism. However, currently there remains a\nperformance gap to more expressive stochastic RNN variants, especially those\nwith several layers of dependent random variables. In this work, we propose\nstochastic temporal convolutional networks (STCNs), a novel architecture that\ncombines the computational advantages of temporal convolutional networks (TCN)\nwith the representational power and robustness of stochastic latent spaces. In\nparticular, we propose a hierarchy of stochastic latent variables that captures\ntemporal dependencies at different time-scales. The architecture is modular and\nflexible due to the decoupling of the deterministic and stochastic layers. We\nshow that the proposed architecture achieves state of the art log-likelihoods\nacross several tasks. Finally, the model is capable of predicting high-quality\nsynthetic samples over a long-range temporal horizon in modeling of handwritten\ntext.","url_abs":"http://arxiv.org/abs/1902.06568v1","url_pdf":"http://arxiv.org/pdf/1902.06568v1.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":"stcn-stochastic-temporal-convolutional","repo_url":"https://github.com/emreaksan/stcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.06568","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}