{"id":"W4416368650","doi":"10.1109/tase.2025.3634511","title":"Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"NextGenerationEU; Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Frequentist inference; Artificial neural network; Deep learning; Gradient descent; Parametric statistics; Inference; Bayesian probability; Convergence (economics); Approximate inference","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001696446,0.0008908466,0.001067693,0.0006481369,0.0003287221,0.0007356948,0.001701188,0.001122884,0.001607685],"category_scores_gemma":[0.004938348,0.0006655802,0.0006047889,0.0005569819,0.0008715841,0.001307985,0.001084648,0.001492617,0.0004040803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001284095,"about_ca_system_score_gemma":0.001823179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01338265,"about_ca_topic_score_gemma":0.01624875,"domain_scores_codex":[0.9996,0.0001257142,0.00002210078,0.00007861602,0.0001230184,0.0000506933],"domain_scores_gemma":[0.9988538,0.0006961245,0.0001111445,0.00008174282,0.0002063018,0.00005091448],"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":[0.00004741992,0.0000335972,0.0007464673,0.00004562682,0.00003179159,0.00003518163,0.0000383369,0.9454108,0.001172532,0.01163598,0.001040433,0.03976174],"study_design_scores_gemma":[0.000001343384,0.000003353287,0.00003191569,0.000001965642,9.618531e-7,0.000002615276,9.329547e-7,0.9978703,0.0001213935,0.001898099,0.0000656921,0.000001360288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01125174,0.0002747606,0.9872338,0.0001862197,0.00001659967,0.00001884229,0.00005993861,0.0003318006,0.0006264963],"genre_scores_gemma":[0.748131,0.0005623302,0.2457039,0.0002985061,0.00006500127,0.0001759942,0.0005439724,0.0002120578,0.004307243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01338265,"threshold_uncertainty_score":0.02660948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007864199419744623,"score_gpt":0.2550658543270753,"score_spread":0.2472016549073307,"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."}}