{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001881665,0.0007943836,0.0009104663,0.0005012897,0.0004543432,0.0009569625,0.002548651,0.001453927,0.003596171],"category_scores_gemma":[0.004329095,0.0005947035,0.0008881193,0.0008291155,0.001085279,0.002405985,0.002421614,0.0020362,0.0007797955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007114873,"about_ca_system_score_gemma":0.001221156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002170777,"about_ca_topic_score_gemma":0.003780972,"domain_scores_codex":[0.9994801,0.0001545656,0.00003724952,0.00009759322,0.000158017,0.00007246435],"domain_scores_gemma":[0.9990284,0.0003253803,0.0001308199,0.0002519351,0.0001808101,0.00008275965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003601186,0.0002203274,0.0007852357,0.0002566441,0.0001585773,0.0001780248,0.0001303893,0.3512882,0.03452997,0.4100391,0.01319442,0.1888591],"study_design_scores_gemma":[0.00001292596,0.0000384999,0.00009572756,0.000009506892,0.00001316463,0.00003172593,0.000004094697,0.9522515,0.002278758,0.04437657,0.0008773889,0.00001019488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007118775,0.0002129327,0.9901896,0.0003114217,0.00005956377,0.00003018473,0.00008882986,0.0003849904,0.001603676],"genre_scores_gemma":[0.6425893,0.0009709559,0.3421678,0.0005405923,0.000452246,0.0002894111,0.0005732444,0.0003849862,0.01203149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003596171,"threshold_uncertainty_score":0.01203036,"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."}}