{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009806172,0.001894697,0.001329472,0.001171415,0.0009125689,0.001916728,0.001877122,0.001497926,0.01473367],"category_scores_gemma":[0.001519037,0.0004037728,0.001272329,0.001801415,0.0006151942,0.002873419,0.002357436,0.001070583,0.004554315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005839388,"about_ca_system_score_gemma":0.001088086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003192151,"about_ca_topic_score_gemma":0.005340502,"domain_scores_codex":[0.9994286,0.00006529294,0.00004277681,0.0001805461,0.0001511908,0.0001315406],"domain_scores_gemma":[0.9996,0.00005206589,0.00003076141,0.0001646721,0.0001122895,0.00004029388],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007544465,0.0002879296,0.0006759229,0.0003724233,0.000267103,0.0002460414,0.00009889485,0.02431913,0.08585189,0.02174959,0.01514338,0.8502334],"study_design_scores_gemma":[0.00003594796,0.0002970102,0.001894245,0.00007054369,0.0003770443,0.0005262943,0.0001324602,0.8012944,0.1173485,0.04926564,0.02867127,0.00008655782],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02402578,0.001588814,0.9560663,0.0003780323,0.0004149415,0.0000882679,0.0006341086,0.003418087,0.01338571],"genre_scores_gemma":[0.4391128,0.001534824,0.5048354,0.0006427633,0.000465834,0.0002366872,0.002856877,0.00070141,0.04961343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01473367,"threshold_uncertainty_score":0.04928905,"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."}}