{"id":"W4298733999","doi":"10.48550/arxiv.1605.09332","title":"Parametric Exponential Linear Unit for Deep Convolutional Neural\\n Networks","year":2016,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"MNIST database; Parametric statistics; Convolutional neural network; Computer science; Artificial intelligence; Set (abstract data type); Deep learning; Pattern recognition (psychology); Flexibility (engineering); Artificial neural network; Deep neural networks; Realization (probability); Residual neural network; Exponential function; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004204284,0.001023669,0.0008936648,0.0007034831,0.00119377,0.0001899116,0.004371507,0.0008364646,0.0001539488],"category_scores_gemma":[0.0001585347,0.00114462,0.0008779358,0.003268958,0.0007885611,0.001076506,0.003333868,0.00118945,0.0002282661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004801858,"about_ca_system_score_gemma":0.000314688,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002130277,"about_ca_topic_score_gemma":0.00002179939,"domain_scores_codex":[0.9934989,0.0003724359,0.0008464175,0.003447826,0.0002505015,0.001583923],"domain_scores_gemma":[0.9922628,0.002084761,0.001171829,0.002732668,0.0009904052,0.0007575199],"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":[0.000196328,0.0001859421,0.0006830181,0.00003701624,0.0001383658,0.00005108302,0.00002069091,0.7693454,0.00002543373,0.224531,0.0002333529,0.004552396],"study_design_scores_gemma":[0.001800955,0.0001828337,0.0006499646,0.00008363363,0.0002272287,0.00002038428,0.00001660259,0.9254965,0.00005138326,0.06573695,0.004567746,0.001165794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02079276,0.0003730241,0.9727555,0.0004485909,0.002590264,0.002205837,0.0001187848,0.0003900612,0.0003251642],"genre_scores_gemma":[0.9852687,0.000922846,0.009285991,0.0002766467,0.00140218,0.00003909098,0.0001306331,0.00008973625,0.00258423],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9644759,"threshold_uncertainty_score":0.9991004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09866047435014201,"score_gpt":0.2223506805520849,"score_spread":0.1236902062019429,"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."}}