{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001271032,0.00124636,0.0009839085,0.001207895,0.000541901,0.0005751783,0.001368498,0.001042707,0.001181035],"category_scores_gemma":[0.005549364,0.000468121,0.0008334594,0.00105815,0.0007928273,0.001711951,0.001457497,0.001238935,0.0005233121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007331651,"about_ca_system_score_gemma":0.001020924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004954108,"about_ca_topic_score_gemma":0.005759995,"domain_scores_codex":[0.9990253,0.0002354659,0.00006089988,0.0001644156,0.000387723,0.0001261828],"domain_scores_gemma":[0.9985819,0.0005926532,0.0001649734,0.0003586445,0.000257095,0.00004468975],"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":[0.0003880479,0.0002340947,0.002199505,0.0002928593,0.0001529708,0.0004270324,0.0002803787,0.5324375,0.0342274,0.02055306,0.0118309,0.3969763],"study_design_scores_gemma":[0.00001439841,0.00005802003,0.0003703292,0.00001494502,0.00002548662,0.00006585857,0.00001591912,0.9835536,0.005949668,0.008158985,0.001759613,0.00001312657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0939495,0.001700442,0.8976151,0.0006277421,0.0001277675,0.00006342024,0.000326789,0.002773488,0.002815718],"genre_scores_gemma":[0.7203487,0.00132494,0.2715748,0.0004277799,0.0002554291,0.0001925224,0.001251191,0.0005096032,0.004114959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004954108,"threshold_uncertainty_score":0.009850502,"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."}}