{"id":"W3102090196","doi":"","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Inductive bias; Computer science; Focus (optics); Artificial neural network; Artificial intelligence; Symbolic regression; The Symbolic; Deep neural networks; Deep learning; Theoretical computer science; Graph; Machine learning; Multi-task learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004287022,0.0001179926,0.0001311278,0.00005146592,0.0002415199,0.0009308103,0.0003019307,0.00002694813,9.905133e-7],"category_scores_gemma":[0.00001400159,0.00009870694,0.0000234699,0.0004912313,0.00001881988,0.005543018,0.00008375475,0.0001546877,0.0000301917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002499435,"about_ca_system_score_gemma":0.00005750094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001251806,"about_ca_topic_score_gemma":0.000001320942,"domain_scores_codex":[0.9991028,0.00002740241,0.0002744548,0.0001684053,0.0002962501,0.0001306935],"domain_scores_gemma":[0.9992931,0.00006454482,0.0002588129,0.0001177417,0.0001782294,0.00008752413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005439222,0.000006327515,0.00009813199,0.00004047876,0.0000082824,4.273319e-7,0.008275346,0.9347392,0.00009302879,0.01717408,0.00002193485,0.03953734],"study_design_scores_gemma":[0.0001461958,0.00003251098,0.0003158246,0.00005268474,0.000003923747,0.000004028788,0.0006910151,0.9969935,0.00007368124,0.0007741975,0.000776946,0.0001354292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1125677,0.00007311704,0.8852656,0.0005907588,0.0000584666,0.0001645592,0.000004804719,0.0002505682,0.001024409],"genre_scores_gemma":[0.9960414,0.000001662387,0.003355321,0.0003808631,0.0001132739,0.00004535303,0.00004950071,0.000006626733,0.000006034011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8834737,"threshold_uncertainty_score":0.8975825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03918932432090418,"score_gpt":0.2444299454701833,"score_spread":0.2052406211492791,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}