{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005625748,0.001110513,0.0007544258,0.0006646373,0.0004035668,0.0005318553,0.001525377,0.0006578222,0.007452604],"category_scores_gemma":[0.001708691,0.0005435526,0.0005536859,0.0007660288,0.0003191306,0.001956138,0.0009837718,0.001505201,0.001508291],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009714586,"about_ca_system_score_gemma":0.001337986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009723951,"about_ca_topic_score_gemma":0.01410699,"domain_scores_codex":[0.999622,0.00004375925,0.00002720551,0.0001366608,0.000108154,0.00006217811],"domain_scores_gemma":[0.9995155,0.0001094212,0.00003469307,0.0001453359,0.00015421,0.00004079983],"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":[0.000524965,0.0002692609,0.002985175,0.0002185156,0.0001225815,0.0002160554,0.0001382857,0.2674141,0.06720459,0.009596456,0.007916374,0.6433936],"study_design_scores_gemma":[0.00002747151,0.00006979162,0.0004989712,0.000008421989,0.00001692326,0.00005462081,0.00002234089,0.971801,0.02221894,0.00216477,0.00310705,0.000009646249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1020523,0.0006317346,0.8794631,0.0003775338,0.0002568749,0.0001417047,0.0001977286,0.01018448,0.006694606],"genre_scores_gemma":[0.5164054,0.0002519812,0.4756493,0.000202996,0.00005551787,0.0001948505,0.0007667398,0.0005232732,0.005949931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009723951,"threshold_uncertainty_score":0.02493143,"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."}}