{"id":"W2252143850","doi":"","title":"Training recurrent neural networks","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":391,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Recurrent neural network; Initialization; Computer science; Sequence (biology); Artificial intelligence; Probabilistic logic; Gradient descent; Artificial neural network; Machine 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":[0.00009215784,0.0001743071,0.000182674,0.00007241793,0.00006159161,0.0002169711,0.0007861396,0.0001629004,0.00008726389],"category_scores_gemma":[0.00001318262,0.0001545202,0.00007800807,0.0001123834,0.000003773111,0.0002474766,0.0000525184,0.0003240535,0.00004120708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002210581,"about_ca_system_score_gemma":0.00004493443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000311095,"about_ca_topic_score_gemma":0.00006160525,"domain_scores_codex":[0.9988457,0.00002620504,0.0002426838,0.000413517,0.0002004351,0.0002714857],"domain_scores_gemma":[0.9992852,0.00003273287,0.000104247,0.0004386414,0.00006273187,0.00007644093],"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":[6.853483e-7,0.000005650236,0.000005212399,0.00001256021,0.000007216348,0.000002411768,0.001351625,0.002502441,0.000005225345,0.01880828,0.001037572,0.9762611],"study_design_scores_gemma":[0.00004805985,0.00001374503,0.0001375074,0.00003378873,0.000003769472,0.00000226431,0.000151595,0.997963,0.00001073852,0.0005221151,0.0009251119,0.0001883233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01319252,0.000481867,0.9236661,0.0001309933,0.00703693,0.0002483705,1.825525e-7,0.0003760677,0.05486699],"genre_scores_gemma":[0.8651414,0.00006261159,0.08302503,0.000590175,0.001107177,0.0001118658,0.0002019952,0.00004891532,0.04971082],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9954606,"threshold_uncertainty_score":0.6301152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05334820093018022,"score_gpt":0.2900405536168376,"score_spread":0.2366923526866574,"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."}}