{"id":"W24640360","doi":"10.1007/978-3-319-06483-3_6","title":"Analysis of Feature Maps Selection in Supervised Learning Using Convolutional Neural Networks","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Kernel (algebra); Field (mathematics); Deep learning; Receptive field; Feature selection; Object (grammar); Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002161417,0.0005440473,0.0008042932,0.0008515977,0.0003978803,0.0008712241,0.001130444,0.0006248956,0.001890878],"category_scores_gemma":[0.007273794,0.0002899545,0.0005724045,0.0008348782,0.0004337357,0.001192984,0.0006018569,0.0008212051,0.0002769658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008139303,"about_ca_system_score_gemma":0.0009468158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003814588,"about_ca_topic_score_gemma":0.004973087,"domain_scores_codex":[0.9992035,0.0002570236,0.00004231418,0.0001478351,0.0002630851,0.0000862518],"domain_scores_gemma":[0.9931239,0.005271328,0.0002753215,0.0004194149,0.0008168734,0.00009311729],"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":[0.0007296217,0.0003016804,0.009957045,0.0002219694,0.0002063864,0.0001838097,0.0001041144,0.4920915,0.01148443,0.01399493,0.005839296,0.4648854],"study_design_scores_gemma":[0.000003673921,0.00001751881,0.0009445354,0.000003832592,0.000008856856,0.00001497104,0.000006242104,0.9955227,0.001319663,0.002023572,0.000131353,0.000003037401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2183572,0.001501495,0.7760154,0.0003161726,0.00005898548,0.00006770113,0.0002357694,0.001113136,0.002334176],"genre_scores_gemma":[0.8826118,0.0003411661,0.1123222,0.00006047732,0.00006778152,0.00006971613,0.0007712616,0.0002143794,0.00354132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003814588,"threshold_uncertainty_score":0.0114308,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01629056470674845,"score_gpt":0.243130483783615,"score_spread":0.2268399190768666,"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."}}