{"id":"W2963519357","doi":"10.48550/arxiv.1907.11110","title":"Filter Bank Regularization of Convolutional Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Regularization (linguistics); Convolutional neural network; Generality; Artificial intelligence; Computer science; Robustness (evolution); Pattern recognition (psychology); Kernel (algebra); Reproducing kernel Hilbert space; Mathematics; Algorithm; Hilbert space","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":[0.0005822523,0.0006614998,0.0003852327,0.000377634,0.0002229093,0.000510579,0.0005319546,0.0009016464,0.00106192],"category_scores_gemma":[0.00180118,0.0002816761,0.0004586995,0.0004360997,0.0006516178,0.0006184337,0.0004915365,0.001081352,0.0004313827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007326936,"about_ca_system_score_gemma":0.0007084946,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003420698,"about_ca_topic_score_gemma":0.003364418,"domain_scores_codex":[0.9997159,0.00007653756,0.0000134829,0.00006496631,0.0001021472,0.00002704616],"domain_scores_gemma":[0.9996208,0.0001637528,0.00004375502,0.0000507436,0.0001040148,0.00001696948],"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":[0.00007124765,0.00003647466,0.0006729917,0.0001130368,0.00007923471,0.00006938705,0.0000464584,0.7955532,0.02731743,0.08378873,0.003609955,0.08864186],"study_design_scores_gemma":[0.000002751077,0.000007120518,0.00009646118,0.000004713971,0.000004100047,0.000009763002,0.000001688385,0.9879166,0.002131017,0.008635257,0.001187261,0.000003292062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007556198,0.0003305155,0.9896639,0.0001250933,0.00003700135,0.00001060083,0.00003587149,0.0002056763,0.002035101],"genre_scores_gemma":[0.5892665,0.001933735,0.3927688,0.0003586853,0.0001552654,0.0001867634,0.000452686,0.0002603331,0.01461729],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003420698,"threshold_uncertainty_score":0.006801605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04905353176402946,"score_gpt":0.1874979352050216,"score_spread":0.1384444034409922,"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."}}