{"id":"W2949427968","doi":"10.48550/arxiv.1212.0901","title":"Advances in Optimizing Recurrent Networks","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Music and Audio Processing","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Machine learning; Momentum (technical analysis); Artificial neural network; Economics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002758003,0.000255496,0.0002884716,0.0001962041,0.0001058458,0.0001159634,0.001375333,0.0002121404,0.00002228443],"category_scores_gemma":[0.00001237527,0.0002890839,0.0001105627,0.000548977,0.00006152085,0.001015926,0.001769522,0.0006984637,0.0000216088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001674139,"about_ca_system_score_gemma":0.0001021897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001584713,"about_ca_topic_score_gemma":0.00001935743,"domain_scores_codex":[0.9983889,0.00009153477,0.0001874072,0.0007984583,0.00006485282,0.0004688168],"domain_scores_gemma":[0.99885,0.00005951746,0.0002426514,0.0006549454,0.0000551414,0.0001377521],"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":[0.00001211301,0.00007464878,0.002154735,0.00009706255,0.00001023733,0.000101161,0.0003162656,0.9061481,0.000001788136,0.04456021,0.0001431331,0.04638056],"study_design_scores_gemma":[0.000271412,0.00001324098,0.0003432752,0.0004122125,0.00001550276,0.000002935668,0.00003708204,0.9829713,0.0000175413,0.01279965,0.002642565,0.000473306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007565786,0.003837627,0.976519,0.00007183023,0.001332166,0.0001351997,9.391284e-7,0.0001468094,0.01039062],"genre_scores_gemma":[0.9905617,0.002411747,0.006519467,0.0001272703,0.000172848,8.51658e-7,0.000004595391,0.00001145023,0.0001900492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9829959,"threshold_uncertainty_score":0.9999561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0659870371950261,"score_gpt":0.1981966471180804,"score_spread":0.1322096099230543,"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."}}