{"id":"W2786263712","doi":"","title":"Kronecker-factored Curvature Approximations for Recurrent Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Kronecker delta; Recurrent neural network; Parameterized complexity; Computer science; Algorithm; Covariance; Gaussian; Inverse; Artificial neural network; Applied mathematics; Artificial intelligence; Mathematical optimization; 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":[0.00122656,0.001193668,0.0008959702,0.0006890151,0.0003224058,0.001058303,0.001282917,0.001295828,0.002438084],"category_scores_gemma":[0.005392608,0.0006255998,0.0008748865,0.0006084624,0.0007647215,0.001727752,0.0009610013,0.001801331,0.001265152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001367498,"about_ca_system_score_gemma":0.001171126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006359992,"about_ca_topic_score_gemma":0.008861822,"domain_scores_codex":[0.9995891,0.0001436394,0.00002974976,0.00007386296,0.0001255198,0.00003803997],"domain_scores_gemma":[0.9988877,0.0004907494,0.0001201551,0.0001867232,0.0002490584,0.00006555676],"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":[0.00005007397,0.00002058637,0.000427359,0.00005155039,0.00003028226,0.0000423582,0.0000454503,0.9364405,0.001834366,0.0236565,0.001736441,0.03566454],"study_design_scores_gemma":[9.980854e-7,0.000003514722,0.00002570074,0.000002732469,0.000001097045,0.000005233031,0.000001403757,0.9959967,0.0001597376,0.003583909,0.0002168153,0.00000217326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007426968,0.0003004003,0.9904132,0.0001003954,0.00003061989,0.00001721188,0.00008077035,0.0006711352,0.0009592402],"genre_scores_gemma":[0.466459,0.0006895682,0.5233035,0.0001759344,0.00009776734,0.0001733137,0.0008874765,0.0009629682,0.007250522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006359992,"threshold_uncertainty_score":0.01264596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06065494251667179,"score_gpt":0.3641504852356096,"score_spread":0.3034955427189378,"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."}}