{"id":"W3049569209","doi":"10.1038/s41467-021-26568-2","title":"Correspondence between neuroevolution and gradient descent","year":2021,"lang":"en","type":"preprint","venue":"Nature Communications","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; Vector Institute; University of Ottawa","funders":"Lawrence Berkeley National Laboratory; Office of Science; Basic Energy Sciences; National Energy Research Scientific Computing Center; U.S. Department of Energy","keywords":"Neuroevolution; Gradient descent; Artificial neural network; Limit (mathematics); Computer science; Function (biology); Stochastic gradient descent; Mathematics; Applied mathematics; Artificial intelligence; Algorithm; Mathematical analysis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001657405,0.0005009921,0.0007884566,0.0006646766,0.000619541,0.001377514,0.0009789882,0.001745002,0.003270614],"category_scores_gemma":[0.01311061,0.0003893508,0.0005572108,0.000597701,0.002674604,0.001828578,0.001822338,0.002188574,0.0004322368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001434863,"about_ca_system_score_gemma":0.0009066034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001499799,"about_ca_topic_score_gemma":0.001010957,"domain_scores_codex":[0.9988501,0.0004725972,0.00004463607,0.0001751873,0.0003649306,0.0000925277],"domain_scores_gemma":[0.9955826,0.003172808,0.0003320077,0.0004077771,0.0003397666,0.000165086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002624372,0.00002103765,0.0004395224,0.00005279309,0.00002478427,0.00007729563,0.0001325131,0.1186789,0.0009825078,0.8654712,0.0008959133,0.01319721],"study_design_scores_gemma":[0.00001585453,0.00003176267,0.0004192703,0.00002448418,0.000007697049,0.0001080689,0.00002006715,0.4756772,0.00065983,0.5202677,0.002752588,0.00001554571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0322593,0.0007655798,0.940079,0.001476547,0.0001408168,0.000046099,0.00004625295,0.0002846342,0.0249018],"genre_scores_gemma":[0.8398769,0.0009497833,0.1475106,0.000780157,0.000211417,0.000287256,0.00009165149,0.0003946202,0.009897531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003270614,"threshold_uncertainty_score":0.01094133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03742233270969061,"score_gpt":0.3066605036899532,"score_spread":0.2692381709802626,"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."}}