{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/symbolic-deep-learning","slug":"symbolic-deep-learning","name":"Symbolic Deep Learning","full_name":"Symbolic Deep Learning","full_name_withheld":false,"description_markdown":"This is a general approach to convert a neural network into an analytic equation. The technique works as follows:\r\n\r\n1. Encourage sparse latent representations\r\n2. Apply symbolic regression to approximate the transformations between in/latent/out layers\r\n3. Compose the symbolic expressions.\r\n\r\nIn the [paper](https://arxiv.org/abs/2006.11287), we show that we find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark matter simulation-and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures. The symbolic expressions extracted from the GNN using our technique also generalized to out-of-distribution data better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","paper":"/paper/discovering-symbolic-models-from-deep","first_author":"Miles Cranmer","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/discovering-symbolic-models-from-deep"},"source":{"url":"https://arxiv.org/abs/2006.11287v2","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/MilesCranmer/symbolic_deep_learning","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Graphs","area_id":"graphs","collection":"Graph Models","url":"/methods/category/graph-models","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Interpretability","url":"/methods/category/interpretability","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/discovering-symbolic-models-from-deep","slug":"discovering-symbolic-models-from-deep","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","date":"2020-06-19","arxiv_id":"2006.11287","n_code_links":3,"syntology":{"ran":5,"of":6,"n_ran_checked":5,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["MilesCranmer/PySR","MilesCranmer/symbolic_deep_learning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}],"papers_shown":1,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1,"with_a_code_link":1,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/symbolic-deep-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/symbolic-deep-learning/papers/ran/1","json":"/method/symbolic-deep-learning/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/symbolic-regression","name":"Symbolic Regression","papers":1}],"tasks_shown":2,"n_tasks":2,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/symbolic-deep-learning"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Symbolic%20Deep%20Learning","read_at":"2026-10-05T01:02:49+00:00","query":"Symbolic Deep Learning","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2006.11287","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'Symbolic Deep Learning' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["Symbolic-KAN","Symbolic M-CBE","Symbolic Network","MapSeek-Symbolic","Neuro-symbolic PRM","Symbolic Separation","Symbolic Neural ODEs","neuro-symbolic model"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"9cd6d1f6b6a49259d8495661970c788f22773dcfd7c057b877f8cd6546205fab","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}