{"author":[{"first_name":"Subham","last_name":"Sahoo","full_name":"Sahoo, Subham"},{"orcid":"0000-0001-8622-7887","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","full_name":"Lampert, Christoph","last_name":"Lampert","first_name":"Christoph"},{"first_name":"Georg S","last_name":"Martius","full_name":"Martius, Georg S","id":"3A276B68-F248-11E8-B48F-1D18A9856A87"}],"_id":"6012","external_id":{"arxiv":["1806.07259"],"isi":["000683379204058"]},"quality_controlled":"1","intvolume":"        80","title":"Learning equations for extrapolation and control","user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","month":"02","publication_status":"published","main_file_link":[{"url":"https://arxiv.org/abs/1806.07259","open_access":"1"}],"department":[{"_id":"ChLa"}],"page":"4442-4450","article_processing_charge":"No","date_created":"2019-02-14T15:21:07Z","oa":1,"abstract":[{"text":"We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task.","lang":"eng"}],"citation":{"chicago":"Sahoo, Subham, Christoph Lampert, and Georg S Martius. “Learning Equations for Extrapolation and Control.” In <i>Proceedings of the 35th International Conference on Machine Learning</i>, 80:4442–50. ML Research Press, 2018.","apa":"Sahoo, S., Lampert, C., &#38; Martius, G. S. (2018). Learning equations for extrapolation and control. In <i>Proceedings of the 35th International Conference on Machine Learning</i> (Vol. 80, pp. 4442–4450). Stockholm, Sweden: ML Research Press.","mla":"Sahoo, Subham, et al. “Learning Equations for Extrapolation and Control.” <i>Proceedings of the 35th International Conference on Machine Learning</i>, vol. 80, ML Research Press, 2018, pp. 4442–50.","short":"S. Sahoo, C. Lampert, G.S. Martius, in:, Proceedings of the 35th International Conference on Machine Learning, ML Research Press, 2018, pp. 4442–4450.","ama":"Sahoo S, Lampert C, Martius GS. Learning equations for extrapolation and control. In: <i>Proceedings of the 35th International Conference on Machine Learning</i>. Vol 80. ML Research Press; 2018:4442-4450.","ista":"Sahoo S, Lampert C, Martius GS. 2018. Learning equations for extrapolation and control. Proceedings of the 35th International Conference on Machine Learning. ICML: International Conference on Machine Learning vol. 80, 4442–4450.","ieee":"S. Sahoo, C. Lampert, and G. S. Martius, “Learning equations for extrapolation and control,” in <i>Proceedings of the 35th International Conference on Machine Learning</i>, Stockholm, Sweden, 2018, vol. 80, pp. 4442–4450."},"language":[{"iso":"eng"}],"type":"conference","volume":80,"year":"2018","project":[{"name":"International IST Postdoc Fellowship Programme","grant_number":"291734","_id":"25681D80-B435-11E9-9278-68D0E5697425","call_identifier":"FP7"}],"oa_version":"Preprint","isi":1,"date_published":"2018-02-01T00:00:00Z","publisher":"ML Research Press","date_updated":"2023-10-17T09:50:53Z","publication":"Proceedings of the 35th International Conference on Machine Learning","related_material":{"link":[{"description":"News on IST Homepage","relation":"press_release","url":"https://ist.ac.at/en/news/first-machine-learning-method-capable-of-accurate-extrapolation/"}]},"day":"01","status":"public","ec_funded":1,"scopus_import":"1","conference":{"name":"ICML: International Conference on Machine Learning","location":"Stockholm, Sweden","start_date":"2018-07-10","end_date":"2018-07-15"}}