{"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/designing-recurrent-neural-networks-by","title":"Designing recurrent neural networks by unfolding an l1-l1 minimization algorithm","arxiv_id":"1902.06522","date":"2019-02-18","proceeding":null,"authors":["Hung Duy Le","Huynh Van Luong","Nikos Deligiannis"],"abstract":"We propose a new deep recurrent neural network (RNN) architecture for\nsequential signal reconstruction. Our network is designed by unfolding the\niterations of the proximal gradient method that solves the l1-l1 minimization\nproblem. As such, our network leverages by design that signals have a sparse\nrepresentation and that the difference between consecutive signal\nrepresentations is also sparse. We evaluate the proposed model in the task of\nreconstructing video frames from compressive measurements and show that it\noutperforms several state-of-the-art RNN models.","url_abs":"http://arxiv.org/abs/1902.06522v1","url_pdf":"http://arxiv.org/pdf/1902.06522v1.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":"designing-recurrent-neural-networks-by","repo_url":"https://github.com/dhungle/L1-L1-RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}