{"id":"W2108563286","doi":"10.1109/icassp.2013.6639349","title":"Advances in optimizing recurrent networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":486,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Machine learning; Artificial neural network; Clipping (morphology); Deep 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":[0.00003838969,0.0000479201,0.00005174219,0.00002218455,0.00003464887,0.0000827744,0.0003206584,0.00001565169,0.00003928621],"category_scores_gemma":[0.000001505356,0.00003733261,0.0000157009,0.0002616788,0.000008897614,0.0005819063,0.00009282638,0.00007078653,0.00005838099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007932807,"about_ca_system_score_gemma":0.000003680844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001568784,"about_ca_topic_score_gemma":0.00001827449,"domain_scores_codex":[0.9995237,0.00001021042,0.0001006344,0.0001599188,0.00004973231,0.0001557858],"domain_scores_gemma":[0.9996974,0.00003486239,0.00002089431,0.0001917745,0.00001517892,0.00003987871],"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":[2.135183e-7,0.00002306385,0.0002216741,0.000001060733,3.812545e-7,5.254163e-7,0.00001869577,0.03932835,0.00001679259,0.09890921,0.003023512,0.8584565],"study_design_scores_gemma":[0.00005441449,0.00001122457,0.0007759481,0.00000854796,1.918297e-7,0.000001199769,0.000005620612,0.9826484,0.00002624508,0.005392667,0.01100473,0.00007079441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001036483,0.0009058421,0.9795224,0.001629211,0.0001416893,0.0001491506,2.789299e-8,0.00008630038,0.01652887],"genre_scores_gemma":[0.896386,0.000948197,0.1016783,0.0005678833,0.0000756558,0.0001157481,6.576158e-7,0.000003449038,0.0002240954],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9433201,"threshold_uncertainty_score":0.152238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009799538304525268,"score_gpt":0.2427843495198029,"score_spread":0.2329848112152776,"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."}}