{"id":"W4362681904","doi":"10.1109/csde56538.2022.10089323","title":"Generating Robust Convolutional Networks by Injecting Partial Noise in the Training Data","year":2022,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"MNIST database; Convolutional neural network; Computer science; Noise (video); Artificial intelligence; Generalization; Training set; Deep learning; Data set; Set (abstract data type); Data modeling; Noise measurement; Pattern recognition (psychology); Training (meteorology); Test data; Machine learning; Image (mathematics); Noise reduction; Database; Mathematics","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":[0.001599149,0.001195225,0.0008703135,0.0008069086,0.0002848999,0.0006870038,0.001612143,0.0009255652,0.0009144969],"category_scores_gemma":[0.00799865,0.0006750121,0.0008191218,0.0006502923,0.0007336421,0.001365813,0.001431364,0.001535169,0.0004701465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008001099,"about_ca_system_score_gemma":0.0007725246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002215611,"about_ca_topic_score_gemma":0.002981926,"domain_scores_codex":[0.9990876,0.0001346878,0.00006232163,0.0002971798,0.0003219114,0.00009638617],"domain_scores_gemma":[0.9968697,0.001115373,0.0004430512,0.0009329054,0.0005621578,0.00007676113],"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":[0.0002294631,0.0001566908,0.004720191,0.0001549796,0.0001630055,0.0002560692,0.0001496234,0.7161634,0.06877472,0.01124954,0.003141722,0.1948407],"study_design_scores_gemma":[0.000006407389,0.00004146019,0.0003957999,0.000007417279,0.00001649887,0.0000484283,0.00000742733,0.974794,0.02086784,0.003034692,0.0007712794,0.000008726166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07004593,0.0001153874,0.926199,0.0001854383,0.00005956431,0.00006104742,0.0001676453,0.002178611,0.0009874635],"genre_scores_gemma":[0.6149126,0.0001978012,0.3805175,0.0002917079,0.00006684119,0.0002155591,0.0009577366,0.0005478952,0.002292247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002215611,"threshold_uncertainty_score":0.008457184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07496413801348285,"score_gpt":0.2761934160739817,"score_spread":0.2012292780604988,"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."}}