{"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/nested-lstms","title":"Nested LSTMs","arxiv_id":"1801.10308","date":"2018-01-31","proceeding":null,"authors":["Joel Ruben Antony Moniz","David Krueger"],"abstract":"We propose Nested LSTMs (NLSTM), a novel RNN architecture with multiple\nlevels of memory. Nested LSTMs add depth to LSTMs via nesting as opposed to\nstacking. The value of a memory cell in an NLSTM is computed by an LSTM cell,\nwhich has its own inner memory cell. Specifically, instead of computing the\nvalue of the (outer) memory cell as $c^{outer}_t = f_t \\odot c_{t-1} + i_t\n\\odot g_t$, NLSTM memory cells use the concatenation $(f_t \\odot c_{t-1}, i_t\n\\odot g_t)$ as input to an inner LSTM (or NLSTM) memory cell, and set\n$c^{outer}_t$ = $h^{inner}_t$. Nested LSTMs outperform both stacked and\nsingle-layer LSTMs with similar numbers of parameters in our experiments on\nvarious character-level language modeling tasks, and the inner memories of an\nLSTM learn longer term dependencies compared with the higher-level units of a\nstacked LSTM.","url_abs":"http://arxiv.org/abs/1801.10308v1","url_pdf":"http://arxiv.org/pdf/1801.10308v1.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":"nested-lstms","repo_url":"https://github.com/hannw/nlstm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"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":"https://app.syntology.ai/?focus=1801.10308","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}