{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009759428,0.0002377081,0.0002838757,0.0001458628,0.00009282145,0.00003595511,0.001533076,0.0002514079,0.00002661506],"category_scores_gemma":[0.00001367708,0.0002853363,0.000170725,0.0006401851,0.0001293885,0.0003626813,0.001623699,0.0004536472,0.00002723156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001123441,"about_ca_system_score_gemma":0.00008743743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001102786,"about_ca_topic_score_gemma":0.000003919449,"domain_scores_codex":[0.9984058,0.00009989688,0.0002429639,0.000880569,0.00009440211,0.0002763415],"domain_scores_gemma":[0.9977769,0.0001438043,0.0004067817,0.00135805,0.0002236803,0.00009077098],"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":[0.000008517735,0.00002524897,0.00101317,0.00001597,0.00001960928,0.000006693915,0.0000124991,0.7465934,0.00002255593,0.2517014,0.0003186483,0.0002623726],"study_design_scores_gemma":[0.0002223485,0.00002342675,0.001965978,0.0000308327,0.00002556938,0.000003162149,0.000002935273,0.9554316,0.00005809455,0.04175632,0.0002331589,0.0002465734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01761384,0.00007631219,0.9801859,0.0001462601,0.0005691724,0.0003880872,0.00001577149,0.0001522863,0.0008524001],"genre_scores_gemma":[0.9937149,0.00007024593,0.004222876,0.0001177952,0.0001021922,0.00000186578,0.00008351747,0.00001599844,0.001670571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9761011,"threshold_uncertainty_score":0.9999599,"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."}}