{"id":"W1844261860","doi":"10.48550/arxiv.1301.3584","title":"Revisiting Natural Gradient for Deep Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; DeepMind; Compute Canada","keywords":"Natural (archaeology); Computer science; Artificial intelligence; Geology; Paleontology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.006234697,0.001696879,0.001245813,0.001506339,0.000834254,0.001887212,0.002268417,0.001944146,0.003412025],"category_scores_gemma":[0.02747593,0.0006065776,0.0008626238,0.001043731,0.002050272,0.005178347,0.002815229,0.002795655,0.0008416822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001990848,"about_ca_system_score_gemma":0.002619635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006603812,"about_ca_topic_score_gemma":0.0095542,"domain_scores_codex":[0.9973483,0.001223471,0.0001226967,0.0004359514,0.0007469711,0.000122599],"domain_scores_gemma":[0.9925799,0.004206953,0.0003856942,0.001110205,0.001454469,0.0002627624],"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":[0.000286688,0.0002479226,0.003168881,0.0003097026,0.0001453499,0.00008295223,0.0001467429,0.7188414,0.002733563,0.1174567,0.007685822,0.1488942],"study_design_scores_gemma":[0.00001584097,0.00006718137,0.0001472344,0.00002113187,0.000006633535,0.00002218015,0.00000918909,0.968116,0.001047235,0.02908127,0.001457714,0.000008444632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.029501,0.001234232,0.9606408,0.000745387,0.0002259747,0.000135647,0.0002683972,0.001701715,0.005546739],"genre_scores_gemma":[0.4288446,0.0006674969,0.5645424,0.0005538631,0.000182193,0.0002360052,0.0007231342,0.0007341122,0.003516186],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006603812,"threshold_uncertainty_score":0.03297257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04715239288676829,"score_gpt":0.1881851438096175,"score_spread":0.1410327509228492,"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."}}