{"id":"W2326533993","doi":"10.48550/arxiv.1603.09025","title":"Recurrent Batch Normalization","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Computer science; Recurrent neural network; Batch processing; Transformation (genetics); Artificial intelligence; Generalization; Sequence (biology); Convergence (economics); Artificial neural network; Machine learning; Mathematics","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":[0.001602235,0.001374094,0.001202641,0.0005274754,0.0005196683,0.001195426,0.00352606,0.001248338,0.008423565],"category_scores_gemma":[0.007026495,0.0005745473,0.001139206,0.0008880727,0.0009773332,0.00349954,0.001696921,0.002622338,0.003950239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011467,"about_ca_system_score_gemma":0.001767188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004208412,"about_ca_topic_score_gemma":0.006730072,"domain_scores_codex":[0.9988064,0.0002666248,0.00007774008,0.0004770116,0.000264503,0.0001077854],"domain_scores_gemma":[0.9980829,0.0004744398,0.0001678077,0.0007631776,0.0004313677,0.00008029952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005448519,0.0003540253,0.002205459,0.0003084814,0.0002450396,0.0003061455,0.0003790607,0.2476636,0.06584442,0.07471293,0.02502269,0.5824133],"study_design_scores_gemma":[0.00002204196,0.0000927548,0.000443294,0.00001762771,0.00004835623,0.0001022245,0.00002513564,0.9400682,0.01943129,0.03294067,0.006775536,0.00003281465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01032377,0.0002842073,0.9814873,0.0003422027,0.0002608405,0.00007336998,0.0003617724,0.003823209,0.003043417],"genre_scores_gemma":[0.4712857,0.0005682298,0.5050485,0.0009423464,0.0004585535,0.0005787068,0.002098045,0.001486418,0.01753348],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008423565,"threshold_uncertainty_score":0.02817965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08285591806591706,"score_gpt":0.1873429876226347,"score_spread":0.1044870695567176,"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."}}