{"id":"W2807773073","doi":"10.1016/j.neunet.2018.05.015","title":"A sparsity-based stochastic pooling mechanism for deep convolutional neural networks","year":2018,"lang":"en","type":"article","venue":"Neural Networks","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Science and Technology Planning Project of Guangdong Province; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Pooling; Computer science; Convolutional neural network; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003418056,0.0002873013,0.0002745605,0.00009823338,0.0006733905,0.0002236987,0.0008670102,0.0001790604,0.00002542875],"category_scores_gemma":[0.00008799334,0.000275391,0.0001783403,0.0003804398,0.000110362,0.0002358192,0.0002174774,0.000406805,0.00001424805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004347232,"about_ca_system_score_gemma":0.00003345887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000345854,"about_ca_topic_score_gemma":0.00004005366,"domain_scores_codex":[0.997801,0.0001300412,0.0003041598,0.0006316985,0.0002858471,0.000847266],"domain_scores_gemma":[0.9984999,0.0003923172,0.0001647714,0.0004833084,0.0002341733,0.0002255108],"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":[0.00006487728,0.00003333073,0.0001180999,0.000005922328,0.00001477109,0.000006507167,0.0000458348,0.9599885,0.000008714645,0.02063749,0.0007982153,0.01827777],"study_design_scores_gemma":[0.0008062216,0.0003716419,0.0003625027,0.00001837498,0.00002063737,0.00002873585,0.000003110119,0.9956082,0.000007553093,0.002263695,0.0002049791,0.000304412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01399005,0.0001233795,0.9811373,0.001359829,0.002585931,0.0003128365,0.000001974296,0.0004134261,0.00007526266],"genre_scores_gemma":[0.9788972,9.372808e-7,0.01456482,0.004052189,0.002305681,0.0000376402,0.00002533152,0.0000290536,0.00008715608],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9665725,"threshold_uncertainty_score":0.9999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01580560592773382,"score_gpt":0.245903626437773,"score_spread":0.2300980205100391,"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."}}