{"id":"W2465934950","doi":"10.1007/s11063-017-9733-0","title":"Deep Learning with Darwin: Evolutionary Synthesis of Deep Neural Networks","year":2017,"lang":"en","type":"preprint","venue":"Neural Processing Letters","topic":"Machine Learning in Materials Science","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Ancestor; Deep learning; Computer science; Artificial neural network; Artificial intelligence; Modern evolutionary synthesis; Deep neural networks; Recurrent neural network; Natural selection; Darwin (ADL); Biology; Selection (genetic algorithm); Evolutionary biology; Geography","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001030963,0.0007208454,0.001010832,0.0002151672,0.001125284,0.001037752,0.002335771,0.0003227518,0.0003221084],"category_scores_gemma":[0.0008360039,0.000600921,0.0001709549,0.0001715836,0.001268169,0.000722001,0.001282256,0.001478532,0.00002146623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001267862,"about_ca_system_score_gemma":0.0001196757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001963422,"about_ca_topic_score_gemma":0.0000152568,"domain_scores_codex":[0.9951024,0.0006089137,0.0007837902,0.001422985,0.00109735,0.0009845268],"domain_scores_gemma":[0.9961032,0.0002999163,0.002073059,0.001091665,0.0002411378,0.0001910206],"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":[0.00013902,0.00002751127,0.003458816,0.000684245,0.00001211382,0.00006952035,0.0004198356,0.8882409,0.08634926,0.000003260575,0.00006033116,0.02053518],"study_design_scores_gemma":[0.0002034118,0.00008404742,0.00892396,0.0006435244,0.0001168528,0.0001135703,0.00006240048,0.9849172,0.004076934,0.00004934259,0.00004608203,0.0007626849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388332,0.0009174907,0.05353994,0.002891491,0.002200662,0.000496258,0.00001017233,0.0005185088,0.0005922571],"genre_scores_gemma":[0.9841721,0.00001048486,0.01437188,0.0005131439,0.0006675129,0.00009663851,0.0000246546,0.0001084367,0.00003516468],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09667629,"threshold_uncertainty_score":0.9999993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01299707196696077,"score_gpt":0.2532562544121356,"score_spread":0.2402591824451748,"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."}}