{"id":"W1877062207","doi":"","title":"Scaling up Natural Gradient by Sparsely Factorizing the Inverse Fisher Matrix","year":2015,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Stochastic gradient descent; Gradient descent; Covariance matrix; Algorithm; Scaling; Fisher information; Gaussian; Mathematics; Matrix (chemical analysis); Applied mathematics; Computer science; Inverse; Mathematical optimization; Gradient method; Artificial intelligence; Statistics; Artificial neural network","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":[0.001225644,0.00119831,0.0008738205,0.0006405856,0.0004767597,0.0006500407,0.001038554,0.0009999131,0.003634911],"category_scores_gemma":[0.007761017,0.0005511154,0.0006532883,0.0005863989,0.001017548,0.001711942,0.001191971,0.001473312,0.001701923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000707639,"about_ca_system_score_gemma":0.001213211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005505772,"about_ca_topic_score_gemma":0.009356094,"domain_scores_codex":[0.9995182,0.0001758767,0.00002576063,0.0001001711,0.0001332644,0.00004685263],"domain_scores_gemma":[0.9985034,0.0007101246,0.000106046,0.0003663831,0.0002613018,0.00005274081],"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":[0.0001308568,0.0001005359,0.001259309,0.0001674312,0.00008075051,0.0001374281,0.0001554655,0.6588328,0.02099123,0.05962272,0.008774895,0.2497465],"study_design_scores_gemma":[0.000005920111,0.00002031127,0.00009693559,0.000004609712,0.000003717615,0.00002933233,0.000005133974,0.9891794,0.001336293,0.008333681,0.0009765074,0.000008080759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006888942,0.00007244354,0.9912063,0.0000830612,0.00003202594,0.00003001532,0.00003247708,0.0007495511,0.0009050409],"genre_scores_gemma":[0.1920885,0.0001752041,0.8045977,0.0001708093,0.00006426634,0.0001208525,0.0002060329,0.0003382336,0.002238429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005505772,"threshold_uncertainty_score":0.01215994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.068452524059194,"score_gpt":0.2633277899671421,"score_spread":0.1948752659079481,"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."}}