{"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/inferring-algorithmic-patterns-with-stack","title":"Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets","arxiv_id":"1503.01007","date":"2015-03-03","proceeding":"NeurIPS 2015 12","authors":["Armand Joulin","Tomas Mikolov"],"abstract":"Despite the recent achievements in machine learning, we are still very far\nfrom achieving real artificial intelligence. In this paper, we discuss the\nlimitations of standard deep learning approaches and show that some of these\nlimitations can be overcome by learning how to grow the complexity of a model\nin a structured way. Specifically, we study the simplest sequence prediction\nproblems that are beyond the scope of what is learnable with standard recurrent\nnetworks, algorithmically generated sequences which can only be learned by\nmodels which have the capacity to count and to memorize sequences. We show that\nsome basic algorithms can be learned from sequential data using a recurrent\nnetwork associated with a trainable memory.","url_abs":"http://arxiv.org/abs/1503.01007v4","url_pdf":"http://arxiv.org/pdf/1503.01007v4.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":"inferring-algorithmic-patterns-with-stack","repo_url":"https://github.com/facebook/Stack-RNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"inferring-algorithmic-patterns-with-stack","repo_url":"https://github.com/bdusell/stack-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"inferring-algorithmic-patterns-with-stack","repo_url":"https://github.com/fakeNetflix/facebook-repo-Stack-RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"inferring-algorithmic-patterns-with-stack","repo_url":"https://github.com/yandexdataschool/AgentNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.01007","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}