{"id":"W4405717783","doi":"10.1109/tnnls.2024.3516035","title":"Learn to Supervise: Deep Reinforcement Learning-Based Prototype Refinement for Few-Shot Motor Fault Diagnosis","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Machine Fault Diagnosis Techniques","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Guangzhou Municipal Science and Technology Project; National Natural Science Foundation of China","keywords":"Reinforcement learning; Shot (pellet); One shot; Fault (geology); Computer science; Artificial intelligence; Motor learning; Machine learning; Engineering; Psychology; Neuroscience; Mechanical engineering; Materials science; Seismology; Geology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004563964,0.0004198748,0.0004023738,0.0003088039,0.0004030645,0.0003616303,0.0001605881,0.0001957916,0.00008024288],"category_scores_gemma":[0.00002449185,0.0003943023,0.0001887358,0.0003706474,0.00002569796,0.000135896,0.000003003388,0.001056469,0.00001724327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001577235,"about_ca_system_score_gemma":0.00001418007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001543338,"about_ca_topic_score_gemma":0.00005112454,"domain_scores_codex":[0.9979694,0.0001532966,0.0005071912,0.0005066377,0.0002822798,0.0005811438],"domain_scores_gemma":[0.9988907,0.0005272393,0.0000422689,0.0002363851,0.00007019632,0.0002332224],"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":[0.00008207091,0.00003313527,0.0000995349,0.0006501335,0.00008434732,0.000009950004,0.0001619481,0.9622532,0.0001615524,0.00001392373,0.000866914,0.03558332],"study_design_scores_gemma":[0.0003110355,0.001529907,0.000036171,0.0005505529,0.0000686639,0.000008725832,0.00006251226,0.9349866,0.0005968665,8.310976e-7,0.06144278,0.0004053838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02639813,0.001435053,0.9647952,0.00032514,0.00142544,0.003276941,0.000009154465,0.002212521,0.0001224411],"genre_scores_gemma":[0.9903715,0.0002350317,0.0002587999,0.0001073467,0.0002783875,0.007866296,0.0000250511,0.000146431,0.0007111314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9645364,"threshold_uncertainty_score":0.9998509,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01632708788394448,"score_gpt":0.267595405969437,"score_spread":0.2512683180854925,"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."}}