{"id":"W4387129549","doi":"10.1109/access.2023.3320642","title":"Frequency Regularization: Reducing Information Redundancy in Convolutional Neural Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Frequency domain; Regularization (linguistics); Computer science; Convolutional neural network; Redundancy (engineering); Algorithm; Artificial neural network; Reduction (mathematics); Pattern recognition (psychology); Artificial intelligence; Mathematics; Computer vision","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":[0.0001806106,0.0001222284,0.0001179036,0.0002520043,0.0001949263,0.0002642345,0.001085572,0.00007290905,0.000008371947],"category_scores_gemma":[0.00004185593,0.0001327809,0.00003379934,0.002969449,0.00004548748,0.004790692,0.0002117259,0.000201628,0.00006433213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008404448,"about_ca_system_score_gemma":0.00005107317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002909971,"about_ca_topic_score_gemma":0.00001190715,"domain_scores_codex":[0.9986968,0.00004715803,0.0003894614,0.0002826337,0.000241927,0.0003420414],"domain_scores_gemma":[0.9990752,0.0001023471,0.0001561419,0.0004929683,0.0001053171,0.00006800533],"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":[0.000002786971,0.00001445581,0.003326018,0.000009842563,0.000003758028,0.000007435339,0.0001682719,0.9009827,0.0001905877,0.06908399,0.003557174,0.02265296],"study_design_scores_gemma":[0.0001965516,0.000008064824,0.02520609,0.00002035937,0.000001426819,0.00001088036,0.000004545388,0.9444022,0.0002065052,0.02938682,0.0003990027,0.0001575035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03511038,0.00005495896,0.9596568,0.002270796,0.001048479,0.0003410213,0.000003127208,0.0005656934,0.0009487339],"genre_scores_gemma":[0.9936601,0.0000328511,0.005262218,0.0004971099,0.0002278993,0.0001401266,0.00006946272,0.000009420596,0.0001008362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9585497,"threshold_uncertainty_score":0.541465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02709631283056364,"score_gpt":0.295344432431939,"score_spread":0.2682481196013753,"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."}}