{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002695347,0.0002264509,0.0002106721,0.00004517287,0.0006052091,0.0001548109,0.0009365685,0.00007306974,0.0000037677],"category_scores_gemma":[0.00005800336,0.0002348284,0.0001287307,0.0006701318,0.0000838526,0.0003171173,0.000467625,0.0001904959,0.00001847688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006126141,"about_ca_system_score_gemma":0.0000343697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005772944,"about_ca_topic_score_gemma":0.000004877275,"domain_scores_codex":[0.9978659,0.00009812069,0.0003713007,0.0007808504,0.0002092256,0.0006746131],"domain_scores_gemma":[0.9983816,0.000549801,0.0001912575,0.0005056236,0.0002197284,0.0001520018],"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":[0.00004109695,0.00008697482,0.001394985,0.00001567135,0.00003413112,0.00001087721,0.0001396063,0.2361858,0.0008900182,0.1612663,0.005234381,0.5947002],"study_design_scores_gemma":[0.0003698224,0.0001065138,0.002008938,0.000008936067,0.000007750844,0.0001088605,0.000002745047,0.9826905,0.0001167713,0.007067655,0.007296277,0.000215247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004222086,0.00005572099,0.9920366,0.001316944,0.0009632197,0.0004887783,0.000004031198,0.000495778,0.0004168285],"genre_scores_gemma":[0.4992227,7.368032e-7,0.4963302,0.002923402,0.001443597,0.00004177764,0.000004155633,0.00001534959,0.00001810522],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7465047,"threshold_uncertainty_score":0.9576024,"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."}}