{"id":"W2891365890","doi":"10.1016/j.neucom.2018.07.079","title":"AlphaMEX: A smarter global pooling method for convolutional neural networks","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Pooling; Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology); Normalization (sociology); Feature (linguistics); Artificial neural network; Activation function; Deep learning; Machine learning","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":[0.00136186,0.002067864,0.001109274,0.0009893111,0.000505976,0.000801967,0.002234589,0.001047458,0.004750499],"category_scores_gemma":[0.001764906,0.0007155846,0.001394948,0.0007606732,0.0006859301,0.003114254,0.002152186,0.002018174,0.001433943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006330587,"about_ca_system_score_gemma":0.0009837099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002601505,"about_ca_topic_score_gemma":0.004563795,"domain_scores_codex":[0.9994653,0.00008709221,0.00004141531,0.0001611443,0.0001653912,0.00007966941],"domain_scores_gemma":[0.999608,0.00007181095,0.00004688348,0.0001536384,0.00008544718,0.00003435215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006744948,0.0002224304,0.002056366,0.0004000484,0.0005491676,0.0004576088,0.0001490206,0.08481824,0.08915132,0.01598835,0.02579111,0.7797417],"study_design_scores_gemma":[0.0001635383,0.0006369131,0.003038474,0.00006417104,0.0001787372,0.0006649771,0.00004723245,0.8189041,0.1259267,0.01783883,0.03242979,0.0001064314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02283641,0.001236256,0.9648748,0.0002332714,0.0002002994,0.0001321912,0.0004258014,0.007845176,0.002215861],"genre_scores_gemma":[0.3275788,0.00126294,0.6500261,0.0006860764,0.0002228288,0.0004540647,0.002427029,0.001183304,0.01615883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004750499,"threshold_uncertainty_score":0.01589197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02161796267329609,"score_gpt":0.3205610494819621,"score_spread":0.298943086808666,"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."}}