{"id":"W1984083252","doi":"10.1109/smc.2014.6974106","title":"Modular deep Recurrent Neural Network: Application to quadrotors","year":2014,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Recurrent neural network; Modular design; Feed forward; Modularity (biology); Computer science; Feedforward neural network; Layer (electronics); Artificial intelligence; Artificial neural network; Process (computing); Set (abstract data type); Control engineering; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003064183,0.0005441409,0.0004412559,0.000231326,0.000206635,0.0003177059,0.0005242029,0.0005368023,0.001697347],"category_scores_gemma":[0.0007467413,0.0002197297,0.0003876847,0.0003473567,0.000270434,0.0004710607,0.0004736532,0.000470705,0.000290235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004548281,"about_ca_system_score_gemma":0.000266279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00730626,"about_ca_topic_score_gemma":0.007323492,"domain_scores_codex":[0.9999126,0.00002100268,0.000004941819,0.00002809741,0.00002186121,0.00001160376],"domain_scores_gemma":[0.9998184,0.00006541278,0.0000303594,0.00002559535,0.00004403424,0.00001629637],"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":[0.00005587706,0.00002402094,0.0008112509,0.00006558977,0.00002775842,0.000283822,0.00003786842,0.9474121,0.007957621,0.004150049,0.0007889195,0.03838503],"study_design_scores_gemma":[0.000001873408,0.00001773308,0.0001506082,0.00000175085,0.000002515715,0.000023249,0.000003841066,0.9979482,0.0008034384,0.0007272139,0.0003169386,0.000002612778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1502389,0.001155866,0.8350126,0.0003741101,0.0001637259,0.00005149674,0.0003041241,0.00222941,0.01046976],"genre_scores_gemma":[0.9251953,0.0002455118,0.07134595,0.00004309957,0.000021229,0.00001879132,0.0001456732,0.00006970371,0.002914816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00730626,"threshold_uncertainty_score":0.01452744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00957349713561455,"score_gpt":0.241549658472091,"score_spread":0.2319761613364765,"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."}}