{"id":"W4283394502","doi":"10.1007/s00521-022-07227-z","title":"CS-RNN: efficient training of recurrent neural networks with continuous skips","year":2022,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Music and Audio Processing","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Recurrent neural network; Computer science; Artificial intelligence; Metric (unit); Hyperparameter; Machine learning; Task (project management); Inference; Sequence (biology); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002053299,0.0001138797,0.0001736405,0.00005317204,0.0007111627,0.00007857348,0.0003849884,0.00001608476,0.000003144225],"category_scores_gemma":[0.000004334667,0.0001008978,0.00003412907,0.0004840351,0.00007239114,0.00004461039,0.0003295303,0.0002544035,2.821344e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001422049,"about_ca_system_score_gemma":0.00002770889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006357334,"about_ca_topic_score_gemma":5.994574e-7,"domain_scores_codex":[0.9989227,0.00005801857,0.0002259966,0.0003537874,0.0002016395,0.0002378792],"domain_scores_gemma":[0.9993314,0.0001131424,0.0001956347,0.0002420939,0.00004919908,0.00006850941],"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":[0.000005531102,0.0000726962,0.0004758108,0.00001874673,0.000007254425,0.000002522037,0.001409677,0.3594299,0.0001126753,0.006345327,0.0001410272,0.6319788],"study_design_scores_gemma":[0.000222554,0.0001046084,0.0008382353,0.00001418035,0.000007669745,0.00007225397,0.0002341471,0.9964884,0.00003231247,0.00007101153,0.001787991,0.0001266713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3194635,0.0003500282,0.67864,0.0006966809,0.0001080029,0.0002187447,0.000002389875,0.000125657,0.0003950061],"genre_scores_gemma":[0.9940363,0.000001518819,0.005424628,0.0003686829,0.00010024,0.00003896086,0.000004694788,0.000007883687,0.00001714155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6745728,"threshold_uncertainty_score":0.5469761,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01941660150239913,"score_gpt":0.2483096997675698,"score_spread":0.2288930982651707,"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."}}