{"id":"W2895814028","doi":"10.1109/disa.2018.8490611","title":"Influence of Positive Additive Noise on Classification Performance of Convolutional Neural Networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agentúra na Podporu Výskumu a Vývoja; Canadian Institute for Advanced Research","keywords":"Convolutional neural network; MNIST database; Computer science; Noise (video); Artificial intelligence; Deep learning; Process (computing); Artificial neural network; Pattern recognition (psychology); Set (abstract data type); Speech recognition; Machine learning; Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006331939,0.001511888,0.001130855,0.0009861693,0.0007703922,0.001692363,0.0008861535,0.001721372,0.0007822001],"category_scores_gemma":[0.04967849,0.000451903,0.0006247938,0.000708961,0.001418839,0.001700731,0.001502039,0.001267495,0.0004413024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009250023,"about_ca_system_score_gemma":0.0009042964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005845431,"about_ca_topic_score_gemma":0.00522368,"domain_scores_codex":[0.9940003,0.001563235,0.0007247595,0.001174975,0.001803271,0.000733514],"domain_scores_gemma":[0.971528,0.02169289,0.001389194,0.002177128,0.00257696,0.0006357201],"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":[0.00699793,0.0009860968,0.07360654,0.0007038306,0.0008016807,0.001164513,0.0004243037,0.6520488,0.06279399,0.002761113,0.004450321,0.193261],"study_design_scores_gemma":[0.000112826,0.001909489,0.03890833,0.0001777516,0.0004444484,0.000674198,0.000252584,0.8639658,0.08828355,0.00369819,0.001450157,0.0001226817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9666817,0.002735209,0.02474769,0.0007859512,0.0003445624,0.00005600393,0.000396926,0.0008190239,0.003432975],"genre_scores_gemma":[0.9947842,0.0003104341,0.003443256,0.0001695365,0.00005949039,0.00001637229,0.0005251014,0.00007071358,0.0006208134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006331939,"threshold_uncertainty_score":0.0334869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01473576330331762,"score_gpt":0.2559942067152896,"score_spread":0.241258443411972,"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."}}