{"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-equations-for-extrapolation-and","title":"Learning Equations for Extrapolation and Control","arxiv_id":"1806.07259","date":"2018-06-19","proceeding":"ICML 2018 7","authors":["Subham S. Sahoo","Christoph H. Lampert","Georg Martius"],"abstract":"We present an approach to identify concise equations from data using a\nshallow neural network approach. In contrast to ordinary black-box regression,\nthis approach allows understanding functional relations and generalizing them\nfrom observed data to unseen parts of the parameter space. We show how to\nextend the class of learnable equations for a recently proposed equation\nlearning network to include divisions, and we improve the learning and model\nselection strategy to be useful for challenging real-world data. For systems\ngoverned by analytical expressions, our method can in many cases identify the\ntrue underlying equation and extrapolate to unseen domains. We demonstrate its\neffectiveness by experiments on a cart-pendulum system, where only 2 random\nrollouts are required to learn the forward dynamics and successfully achieve\nthe swing-up task.","url_abs":"http://arxiv.org/abs/1806.07259v1","url_pdf":"http://arxiv.org/pdf/1806.07259v1.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-equations-for-extrapolation-and","repo_url":"https://github.com/martius-lab/EQL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.07259","atlas_url":"https://app.syntology.ai/?focus=1806.07259","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}