{"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/learning-simple-algorithms-from-examples","title":"Learning Simple Algorithms from Examples","arxiv_id":"1511.07275","date":"2015-11-23","proceeding":null,"authors":["Wojciech Zaremba","Tomas Mikolov","Armand Joulin","Rob Fergus"],"abstract":"We present an approach for learning simple algorithms such as copying,\nmulti-digit addition and single digit multiplication directly from examples.\nOur framework consists of a set of interfaces, accessed by a controller.\nTypical interfaces are 1-D tapes or 2-D grids that hold the input and output\ndata. For the controller, we explore a range of neural network-based models\nwhich vary in their ability to abstract the underlying algorithm from training\ninstances and generalize to test examples with many thousands of digits. The\ncontroller is trained using $Q$-learning with several enhancements and we show\nthat the bottleneck is in the capabilities of the controller rather than in the\nsearch incurred by $Q$-learning.","url_abs":"http://arxiv.org/abs/1511.07275v2","url_pdf":"http://arxiv.org/pdf/1511.07275v2.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":"learning-simple-algorithms-from-examples","repo_url":"https://github.com/wojzaremba/algorithm-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.07275","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}