{"id":"W2946350616","doi":"10.1109/tnnls.2019.2911603","title":"Convolutional Neural Networks as Asymmetric Volterra Models Based on Generalized Orthonormal Basis Functions","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Control Systems and Identification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Orthonormal basis; Convolutional neural network; Noise (video); Computer science; Nonlinear system; System identification; Quadcopter; Nonlinear system identification; Basis (linear algebra); Applied mathematics; Artificial neural network; Basis function; Dynamical systems theory; Volterra series; Identification (biology); Orthogonal functions; Algorithm; Artificial intelligence; Mathematics; Data modeling; Mathematical analysis; Engineering; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003722272,0.0003793769,0.0004488894,0.0003868514,0.0005493173,0.0002802819,0.0001296172,0.0002540346,0.00008292343],"category_scores_gemma":[0.0000048404,0.0003674476,0.0002301644,0.0005864946,0.00003276638,0.0003402109,0.000001737375,0.001004161,0.00004782568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001132979,"about_ca_system_score_gemma":0.00001482875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00040112,"about_ca_topic_score_gemma":0.00003439243,"domain_scores_codex":[0.9977831,0.0003235377,0.0005664219,0.0004802487,0.0003437038,0.0005030027],"domain_scores_gemma":[0.9989477,0.0002961995,0.0001276852,0.0003355085,0.0000968404,0.0001960712],"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":[0.0001096218,0.00003734086,0.0002494314,0.00004537699,0.00007557951,0.00000271156,0.00002687137,0.9903048,0.00006727052,0.00006137329,0.000321051,0.008698628],"study_design_scores_gemma":[0.001161779,0.0002581555,0.0007196553,0.00008062812,0.00006630764,0.00003131062,0.00006942364,0.9961804,0.000004335338,0.000001033609,0.001059029,0.0003679612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1719774,0.0008827026,0.8189962,0.00006005482,0.006177722,0.0006971564,0.00001482181,0.00048755,0.0007064636],"genre_scores_gemma":[0.9965486,0.00006409239,0.00001148593,0.00008765449,0.0005040201,0.0001701771,0.00004438256,0.00007991838,0.002489671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8245713,"threshold_uncertainty_score":0.9998778,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009914220327719762,"score_gpt":0.1922569441142461,"score_spread":0.1823427237865263,"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."}}