{"id":"W2735234465","doi":"10.1109/ijcnn.2017.7966138","title":"State initialization for recurrent neural network modeling of time-series data","year":2017,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Recurrent neural network; Artificial neural network; Computer science; Time series; Context (archaeology); Artificial intelligence; Echo state network; Time delay neural network; Series (stratigraphy); State (computer science); Network model; Machine learning; Algorithm","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":[0.0001385083,0.00005637135,0.00008491601,0.000009756042,0.0002890705,0.0001759659,0.001305006,0.000014204,0.000003976219],"category_scores_gemma":[0.00001901005,0.00004786517,0.0000193308,0.00004581827,0.00002395862,0.0008542709,0.0005472464,0.00002774578,0.000003007076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002672239,"about_ca_system_score_gemma":0.00001607253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001603461,"about_ca_topic_score_gemma":0.00002995635,"domain_scores_codex":[0.9994112,0.0000100576,0.0001604591,0.0002143758,0.00007287622,0.000131076],"domain_scores_gemma":[0.9986047,0.00002762053,0.0001204438,0.001146232,0.00007135617,0.0000296742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000286382,0.00005144825,0.000192435,0.00002606889,0.00001755531,5.435936e-7,0.00008241938,0.6693525,0.0001359956,0.1296601,0.02440339,0.1760489],"study_design_scores_gemma":[0.00007714211,0.00003034232,0.00003289979,0.000009279724,0.000002975056,6.142636e-7,8.738394e-7,0.9861348,0.00007084692,0.01153369,0.002048653,0.00005782333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001642462,0.00003242739,0.9961846,0.001065497,0.000197431,0.0001956932,0.00001991151,0.00004476725,0.0006171525],"genre_scores_gemma":[0.8607601,0.0001211171,0.1379241,0.0001681045,0.0003392859,0.00003627512,0.0001248182,0.00001155183,0.000514666],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8591176,"threshold_uncertainty_score":0.2425047,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1031324033017408,"score_gpt":0.3308172247859499,"score_spread":0.2276848214842091,"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."}}