{"id":"W1998656041","doi":"10.1109/icassp.2014.6854680","title":"Sequence training of multiple deep neural networks for better performance and faster training speed","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Speedup; Training (meteorology); Discriminative model; Sequence (biology); Deep neural networks; Artificial neural network; Artificial intelligence; Frame (networking); Pattern recognition (psychology); Speech recognition; Parallel computing","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":[0.0001925827,0.0001383912,0.0001961456,0.00004428352,0.0001343231,0.00004367462,0.0004147834,0.00004632986,0.00000285053],"category_scores_gemma":[0.00003236635,0.0001226533,0.00004220748,0.0001955338,0.00009065199,0.0004936738,0.0001142648,0.0001103569,0.00000103762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008482124,"about_ca_system_score_gemma":0.000006624602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001528802,"about_ca_topic_score_gemma":0.000008083918,"domain_scores_codex":[0.9988992,0.00002486101,0.0002592473,0.0003615055,0.0001065388,0.0003486628],"domain_scores_gemma":[0.99896,0.0004490323,0.0001154186,0.0003371857,0.00005388119,0.00008447703],"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":[0.00001009342,0.000009915557,0.002152866,0.00001834616,0.00000713799,2.848516e-7,0.001509115,0.07640937,0.002718025,0.005275254,0.00003413883,0.9118555],"study_design_scores_gemma":[0.0003667039,0.0000901208,0.001926305,0.00001044407,0.000003794021,0.00001350768,0.00004641868,0.995667,0.0004943208,0.0007323897,0.0005017715,0.0001471661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.207671,0.00001317119,0.7911798,0.0004576074,0.00007644359,0.000221058,7.253224e-7,0.00007922935,0.000300946],"genre_scores_gemma":[0.7985668,0.000003196591,0.2004302,0.0008155381,0.0001045891,0.00002572903,0.000002469067,0.00001046225,0.00004102067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9192577,"threshold_uncertainty_score":0.5001655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05802256397119777,"score_gpt":0.2702291253291556,"score_spread":0.2122065613579578,"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."}}