{"id":"W4386743085","doi":"10.36227/techrxiv.24123501.v1","title":"An Autoencoder with Convolutional Neural Network for Surface Defect Detection on Cast Components","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Convolutional neural network; Artificial intelligence; Retraining; Computer science; Pattern recognition (psychology); Convolution (computer science); Cluster analysis; Identification (biology); Artificial neural network; Automation; Image (mathematics); Deep learning; Production (economics); Machine learning; Engineering","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":[0.0003991689,0.0003895361,0.0004153691,0.000118823,0.0002129615,0.0001347895,0.0001409524,0.0005265395,0.00002288583],"category_scores_gemma":[0.00001182814,0.0003361059,0.0002121747,0.0001928991,0.00002209339,0.00008516134,0.00004407281,0.0006474225,0.00007130852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002563631,"about_ca_system_score_gemma":0.00003482361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005628738,"about_ca_topic_score_gemma":0.0005955922,"domain_scores_codex":[0.9982727,0.00009214086,0.0003813146,0.0005045117,0.0003322242,0.0004171599],"domain_scores_gemma":[0.9990893,0.0001642143,0.000101211,0.000398663,0.0001229514,0.0001236328],"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":[0.0001943025,0.00001498119,0.0002253591,0.00008863521,0.0001203436,0.000003610528,0.00002285123,0.995848,0.000657819,0.00003466297,0.001909505,0.0008799536],"study_design_scores_gemma":[0.0007280895,0.0004724524,0.003671598,0.0001655583,0.00005198491,0.0000190285,0.00002694643,0.992031,0.0009374426,0.0001169358,0.001330437,0.0004485243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7031869,0.00003539127,0.2842236,0.0000166601,0.008439799,0.001541689,0.0001447403,0.002017942,0.0003932339],"genre_scores_gemma":[0.9966614,0.000003455709,0.001056824,0.00001867596,0.001400991,0.0001587309,0.0002202067,0.0001315503,0.0003482193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2934744,"threshold_uncertainty_score":0.9999091,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06313484726997855,"score_gpt":0.2685404995117585,"score_spread":0.2054056522417799,"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."}}