{"id":"W4391250552","doi":"10.1109/tie.2024.3352140","title":"Adaptive Attention-Driven Manifold Regularization for Deep Learning Networks: Industrial Predictive Modeling Applications and Beyond","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Regularization (linguistics); Computer science; Artificial intelligence; Deep learning; Machine learning; Manifold (fluid mechanics); 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":[0.0007137093,0.0007575427,0.0006074688,0.0003559059,0.0002191769,0.0004910916,0.0008149865,0.0008290253,0.0006655903],"category_scores_gemma":[0.001623333,0.0002717621,0.0004749819,0.0005109588,0.0005015652,0.0008555142,0.0006480063,0.001213536,0.0001536583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005764469,"about_ca_system_score_gemma":0.0006751086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00547995,"about_ca_topic_score_gemma":0.0043835,"domain_scores_codex":[0.9997808,0.00006771153,0.00001040986,0.00005749257,0.00006042052,0.00002314789],"domain_scores_gemma":[0.9996281,0.0001815538,0.00004307702,0.00003794456,0.00009208599,0.00001724142],"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":[0.00005128309,0.00005013397,0.0008115433,0.00006664057,0.00005343272,0.00006083916,0.00006023109,0.8530453,0.005882782,0.01216513,0.001601818,0.1261509],"study_design_scores_gemma":[5.416446e-7,0.000003261039,0.00003766892,0.000001096084,0.000001138197,0.00000194383,9.176094e-7,0.9985763,0.00021665,0.001043549,0.0001158285,0.000001158056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0186311,0.0008436367,0.978606,0.0003545248,0.00003768273,0.0000167692,0.00003022832,0.0003238919,0.001156077],"genre_scores_gemma":[0.8227028,0.001189967,0.1722497,0.0001994138,0.0001211566,0.00008203178,0.0001867301,0.0000925353,0.003175597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00547995,"threshold_uncertainty_score":0.01089615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01645085674638251,"score_gpt":0.2164183911268994,"score_spread":0.1999675343805169,"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."}}