{"id":"W2913081068","doi":"10.1109/tnnls.2019.2892035","title":"Balanced Decoupled Spatial Convolution for CNNs","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Guangzhou Municipal Science and Technology Project; National Natural Science Foundation of China","keywords":"Redundancy (engineering); Convolution (computer science); Computer science; Decoupling (probability); Filter (signal processing); Algorithm; Spatial analysis; Channel (broadcasting); Spatial filter; Artificial intelligence; Mathematics; Computer vision; Engineering; Telecommunications","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002019402,0.0002104255,0.0002714798,0.00008131273,0.0005000292,0.0001583976,0.0002717228,0.0001159977,0.000006614929],"category_scores_gemma":[0.000004622227,0.0001991459,0.00009779606,0.000290413,0.00003527698,0.0003062707,0.000003807278,0.0004676018,0.00001844389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004297054,"about_ca_system_score_gemma":0.00001322152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005035324,"about_ca_topic_score_gemma":0.00001836789,"domain_scores_codex":[0.9984654,0.0001282388,0.0003058928,0.0005453304,0.0001642636,0.0003909313],"domain_scores_gemma":[0.9987634,0.0005262622,0.0001600872,0.0003532058,0.00007865351,0.0001183934],"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":[0.00003443798,0.0000219768,0.0001169558,0.0000205264,0.0000149617,6.221135e-7,0.00003934093,0.9724434,0.0004575732,0.0007296772,0.00005221874,0.02606832],"study_design_scores_gemma":[0.0006726837,0.0002991417,0.0002889162,0.00004224984,0.00001212424,0.00002384937,0.00002407092,0.9955841,0.00006809364,0.00002969141,0.002732214,0.0002228889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03572173,0.0002026659,0.9606611,0.0002080683,0.001850876,0.0009724177,0.000003393341,0.0003300357,0.00004977568],"genre_scores_gemma":[0.997048,0.00006422013,0.001224102,0.0001193765,0.0002016709,0.0002570936,0.000005439908,0.00002640815,0.001053689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9613263,"threshold_uncertainty_score":0.8120934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01063734284848073,"score_gpt":0.233604971592646,"score_spread":0.2229676287441653,"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."}}