{"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/diagonal-rnns-in-symbolic-music-modeling","title":"Diagonal RNNs in Symbolic Music Modeling","arxiv_id":"1704.05420","date":"2017-04-18","proceeding":null,"authors":["Y. Cem Subakan","Paris Smaragdis"],"abstract":"In this paper, we propose a new Recurrent Neural Network (RNN) architecture.\nThe novelty is simple: We use diagonal recurrent matrices instead of full. This\nresults in better test likelihood and faster convergence compared to regular\nfull RNNs in most of our experiments. We show the benefits of using diagonal\nrecurrent matrices with popularly used LSTM and GRU architectures as well as\nwith the vanilla RNN architecture, on four standard symbolic music datasets.","url_abs":"http://arxiv.org/abs/1704.05420v2","url_pdf":"http://arxiv.org/pdf/1704.05420v2.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":"diagonal-rnns-in-symbolic-music-modeling","repo_url":"https://github.com/ycemsubakan/diagonal_rnns","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"music-modeling","task_name":"Music Modeling"}],"methods":[{"method_slug":"gru","method_name":"GRU"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"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}