{"id":"W2796243302","doi":"10.1109/crv.2018.00059","title":"Convolutional Neural Networks Regularized by Correlated Noise","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Canadian Institute for Advanced Research; University of Waterloo","funders":"Agence Nationale de la Recherche","keywords":"Correlation; Convolutional neural network; Pattern recognition (psychology); Regularization (linguistics); Artificial intelligence; Computer science; Visual cortex; Noise (video); Dropout (neural networks); Differentiable function; Artificial neural network; Mathematics; Neuroscience; Image (mathematics); Machine learning; Psychology","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":[0.00170228,0.001155663,0.001017722,0.0005045887,0.000290056,0.0007668388,0.001175855,0.001155005,0.0006545478],"category_scores_gemma":[0.006673371,0.0006775839,0.000797526,0.0007134138,0.0008996629,0.001692077,0.0007647597,0.001531598,0.000220013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001634083,"about_ca_system_score_gemma":0.001105203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01032467,"about_ca_topic_score_gemma":0.00946894,"domain_scores_codex":[0.9994842,0.0001648101,0.00002929918,0.0001174385,0.0001081011,0.00009614162],"domain_scores_gemma":[0.9984167,0.0007951561,0.0002277313,0.0002740668,0.0002268288,0.0000595669],"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":[0.00009539878,0.00002078769,0.0007498287,0.00002741635,0.00004190481,0.00004174836,0.00002079376,0.9853725,0.002515201,0.004355093,0.0002984544,0.006460923],"study_design_scores_gemma":[0.000003850115,0.00000714398,0.0001145639,0.000001950381,0.000003151869,0.000004120998,9.179384e-7,0.9978089,0.0005263484,0.001483532,0.00004369167,0.000001910852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4402196,0.0008317821,0.5547643,0.0005797039,0.00009071961,0.00004533885,0.0003513578,0.001096459,0.002020812],"genre_scores_gemma":[0.9645671,0.0002369216,0.03297908,0.00009382648,0.00002634257,0.00005361051,0.0003318735,0.00008083443,0.001630329],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01032467,"threshold_uncertainty_score":0.02052921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02015892114808229,"score_gpt":0.238503966376284,"score_spread":0.2183450452282017,"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."}}