{"id":"W7015937534","doi":"","title":"Understanding deep architectures and the effect of unsupervised pre-training","year":2011,"lang":"fr","type":"other","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Université de Montréal; Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canada Research Chairs","keywords":"Deep neural networks; Rule-based system; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008023381,0.0008242814,0.0004801304,0.0003927521,0.0003301993,0.001819784,0.001185509,0.001500451,0.00370003],"category_scores_gemma":[0.005161346,0.0004965421,0.0005424651,0.0003323425,0.0007448696,0.003856111,0.001254605,0.001779356,0.0005345927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007319734,"about_ca_system_score_gemma":0.0006624451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003957985,"about_ca_topic_score_gemma":0.006621164,"domain_scores_codex":[0.9997053,0.0000864479,0.00001541627,0.00009232807,0.00005749946,0.000043114],"domain_scores_gemma":[0.9982863,0.001137715,0.0001255908,0.0002307465,0.0001639003,0.00005580216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002405953,0.0001161307,0.004030556,0.0002170722,0.0001065638,0.0001509896,0.000504809,0.5539817,0.01611195,0.06015155,0.002846341,0.3615417],"study_design_scores_gemma":[0.00001003203,0.00005315334,0.0008726721,0.00002625198,0.00001764255,0.00003727993,0.00003743876,0.9453667,0.004982489,0.04644635,0.002136476,0.00001354479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09785268,0.001719446,0.8880276,0.001520622,0.0001370492,0.00006237629,0.0001365527,0.001085069,0.009458616],"genre_scores_gemma":[0.7954247,0.001904455,0.1861758,0.0004873012,0.0001567709,0.00009079071,0.000337975,0.0002932896,0.01512892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003957985,"threshold_uncertainty_score":0.0123778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01490717462323877,"score_gpt":0.1754797521813107,"score_spread":0.160572577558072,"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."}}