{"id":"W2964335273","doi":"","title":"How to Construct Deep Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Music and Audio Processing","field":"Computer Science","cited_by":582,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Recurrent neural network; Computer science; Deep learning; Artificial intelligence; Construct (python library); Feedforward neural network; Feed forward; Function (biology); Artificial neural network; Engineering","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":[0.0001688021,0.0001275578,0.0001147352,0.0001617805,0.0002290671,0.0009746208,0.0007609122,0.0000389148,0.0001003284],"category_scores_gemma":[0.0004743663,0.0001240069,0.00005428129,0.0002346618,0.0000493279,0.0004448814,0.0001905393,0.0003010761,0.00005004302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003503931,"about_ca_system_score_gemma":0.00003137244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001355466,"about_ca_topic_score_gemma":0.000009008383,"domain_scores_codex":[0.9986789,0.0001178089,0.0001776128,0.0004373162,0.0003776379,0.0002107125],"domain_scores_gemma":[0.9989928,0.0001843177,0.0001342791,0.0002650293,0.0002979397,0.0001256333],"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":[0.00001041338,0.00003604565,0.003878257,0.000003513728,0.00002503041,0.000004841221,0.001274356,0.0520456,0.0003521519,0.3646266,0.001162574,0.5765806],"study_design_scores_gemma":[0.0001795376,0.00007159698,0.002611556,0.00003488198,0.000002858238,0.00001267232,0.0001590925,0.9867647,0.0001104311,0.002118067,0.007780647,0.0001539776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01079298,0.000007066521,0.9349864,0.02375981,0.00112517,0.00009404848,7.856831e-7,0.0001613146,0.02907249],"genre_scores_gemma":[0.9875556,0.000004961417,0.009368742,0.001065621,0.000263156,0.000027507,0.00001441607,0.000007856293,0.001692192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9767626,"threshold_uncertainty_score":0.9398291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03925941227028947,"score_gpt":0.3147329136198822,"score_spread":0.2754735013495928,"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."}}