{"id":"W2120641842","doi":"10.1109/mwscas.2000.952884","title":"Recurrent neural network design for temporal sequence learning","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Recurrent neural network; Artificial neural network; Time delay neural network; Feed forward; Feedforward neural network; Gradient descent; Genetic algorithm; Convergence (economics); Layer (electronics); Artificial intelligence; Sequence (biology); Probabilistic neural network; Phone; Algorithm; Machine learning; 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":[0.0001504184,0.00009345302,0.00008836424,0.00001592689,0.0002606279,0.0001267486,0.0004585706,0.00002762952,0.00003644551],"category_scores_gemma":[0.00001099089,0.00007799509,0.00005266163,0.0002858826,0.00001976373,0.0002205815,0.0000790375,0.0001157373,0.00004317733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001284701,"about_ca_system_score_gemma":0.000005942582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003915213,"about_ca_topic_score_gemma":0.000001797953,"domain_scores_codex":[0.9991242,0.00004452338,0.0001471271,0.0002844423,0.0000954858,0.0003042626],"domain_scores_gemma":[0.999429,0.0001631289,0.00005644923,0.0002364609,0.00003762937,0.00007733826],"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":[0.000003749848,0.00005552416,0.0005035009,0.000006619176,0.000007807467,0.000003992458,0.0001047457,0.3660832,0.0001923016,0.1032016,0.138776,0.3910609],"study_design_scores_gemma":[0.00008685153,0.00009163933,0.00003423788,0.000005020977,0.00000172051,0.000006635074,0.000001880555,0.9554794,0.00005650592,0.002533089,0.04159397,0.0001090453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007535586,0.0001518426,0.9950849,0.002571126,0.0002107441,0.0003137274,3.168427e-7,0.0002528619,0.0006609104],"genre_scores_gemma":[0.6783081,0.00003267087,0.3185555,0.000565088,0.0002890134,0.00011981,0.00000221469,0.000008333096,0.00211931],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6775545,"threshold_uncertainty_score":0.3180548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1143187501704858,"score_gpt":0.2894071848360001,"score_spread":0.1750884346655144,"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."}}