{"id":"W2976519442","doi":"10.36001/phmconf.2019.v11i1.868","title":"Automating Visual Inspection with Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"Annual Conference of the PHM Society","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Context (archaeology); Segmentation; Object detection; Deep learning; Computer vision; Task (project management); Set (abstract data type); Convolution (computer science); Contextual image classification; Image (mathematics); Artificial neural network","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":[],"consensus_categories":[],"category_scores_codex":[0.0001504058,0.0001033833,0.0001445154,0.00001246709,0.0001003459,0.00003010699,0.0000986042,0.000111766,0.00003940083],"category_scores_gemma":[0.000008904641,0.00007047693,0.0001157255,0.000183924,0.00004898182,0.0001813401,0.00003218159,0.0002448717,0.000008297759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004938402,"about_ca_system_score_gemma":0.00002790885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006008611,"about_ca_topic_score_gemma":0.000006353497,"domain_scores_codex":[0.9993322,0.00003284994,0.0001768131,0.0001074187,0.0001992694,0.0001513706],"domain_scores_gemma":[0.9995719,0.0000376595,0.00007767725,0.0001269096,0.0001591277,0.00002667819],"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":[0.0001503524,0.000113759,0.05704438,0.0003258577,0.0006105083,0.000001312131,0.0116461,0.8700888,0.02106443,0.002800748,0.01160253,0.02455128],"study_design_scores_gemma":[0.000393703,0.0001124004,0.01790063,0.00006916204,0.00001267763,0.00001159751,0.001571624,0.9786266,0.0009871845,0.00001557659,0.0001766469,0.0001221684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989993,0.00002774655,0.007604831,0.00003040972,0.000881394,0.0002018138,0.000008241364,0.0001970476,0.001055458],"genre_scores_gemma":[0.9996214,0.000002780047,0.00004432267,0.000021815,0.0001642495,0.000005845813,0.000002933965,0.00001254463,0.0001240974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1085379,"threshold_uncertainty_score":0.2873966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01070046720594132,"score_gpt":0.2109155756680255,"score_spread":0.2002151084620842,"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."}}