{"id":"W2619093102","doi":"10.1007/s11042-017-4840-5","title":"Bi-linearly weighted fractional max pooling","year":2017,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; Canadian Institute for Advanced Research","keywords":"Pooling; Computer science; Convolutional neural network; Reduction (mathematics); Flexibility (engineering); Artificial intelligence; Pattern recognition (psychology); Algorithm; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008165604,0.0001353235,0.0001285435,0.0000461276,0.001296313,0.0005159164,0.0008787011,0.00006562332,0.00001875063],"category_scores_gemma":[0.00003938678,0.0001298016,0.00004181012,0.0001336689,0.0001380394,0.0009036456,0.0002868279,0.0001788964,0.0001832954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001931247,"about_ca_system_score_gemma":0.00003151023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001839294,"about_ca_topic_score_gemma":0.00000694981,"domain_scores_codex":[0.9989329,0.00001143042,0.0002042639,0.0004553793,0.0001640804,0.0002319454],"domain_scores_gemma":[0.998253,0.0002172511,0.0001908941,0.001084196,0.00009455765,0.0001600246],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000317072,0.00009728438,0.001394682,0.000006529225,0.00001707653,0.000001931964,0.00007170723,0.0001189337,0.003148614,0.1399399,0.0008168612,0.8543833],"study_design_scores_gemma":[0.000722446,0.00002455199,0.07290931,0.00001727542,0.0000200205,0.00003118418,0.00001527899,0.4292006,0.002062579,0.03956861,0.4549222,0.0005059027],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002588714,0.0001429996,0.9893697,0.00467455,0.00009497972,0.0005374022,0.0000438738,0.0002146555,0.002333164],"genre_scores_gemma":[0.5112849,0.0003000066,0.4846256,0.000508874,0.0008874867,0.001482464,0.00007093971,0.00002493903,0.0008147458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8538774,"threshold_uncertainty_score":0.9970325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03604117358097957,"score_gpt":0.3005157181237911,"score_spread":0.2644745445428115,"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."}}