{"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/a-seq2seq-approach-to-symbolic-regression","title":"A Seq2Seq approach to Symbolic Regression","arxiv_id":null,"date":"2020-10-17","proceeding":"NeurIPS Workshop LMCA 2020 12","authors":["Luca Biggio","Tommaso Bendinelli","Aurelien Lucchi","Giambattista Parascandolo"],"abstract":"Deep neural networks have proved to be powerful function approximators. The\nlarge hypothesis space they implicitly model allows them to fit very complicated\nblack-box functions to the training data. However, often the data generating\nprocess is characterized by a concise and relatively simple functional form. This\nis especially true in natural sciences, where elegant physical laws govern the\nbehaviour of the quantities of interest. In this work, we address this dichotomy\nfrom the perspective of Symbolic Regression (SR). In particular, we apply a\nfully-convolutional seq2seq model to map numerical data to the corresponding\nsymbolic equations. We demonstrate the effectiveness of our approach on a large\nset of mathematical expressions by providing both a qualitative and a quantitative\nanalysis of our results. Additionally, we release our new equation-generator Python\nlibrary in order to facilitate benchmarking and stimulate new research on SR.","url_abs":"https://openreview.net/forum?id=W7jCKuyPn1","url_pdf":"https://openreview.net/pdf?id=W7jCKuyPn1","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":"a-seq2seq-approach-to-symbolic-regression","repo_url":"https://github.com/symposiumorganization/eqlearner","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"symbolic-regression","task_name":"Symbolic Regression"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}