{"id":"W2967706363","doi":"10.1109/cec.2019.8789964","title":"EvoDNN - An Evolutionary Deep Neural Network with Heterogeneous Activation Functions","year":2019,"lang":"en","type":"article","venue":"","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial neural network; Activation function; Backpropagation; Flexibility (engineering); Artificial intelligence; Evolutionary algorithm; Deep learning; Feature (linguistics); Differentiable function; Evolutionary computation; Function (biology); Stochastic neural network; Time delay neural network; Mathematics; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.00006670786,0.0001296981,0.00009583087,0.00005315143,0.0003106498,0.00007749278,0.0004051068,0.00005014271,0.0001733367],"category_scores_gemma":[0.000001980481,0.0001069323,0.0000402453,0.0005266526,0.00003151301,0.001101566,0.0000941,0.000111213,0.0002791567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005863046,"about_ca_system_score_gemma":0.00004972826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003791626,"about_ca_topic_score_gemma":0.00001617445,"domain_scores_codex":[0.998878,0.00004009066,0.0001487608,0.0004273191,0.0002313466,0.0002744686],"domain_scores_gemma":[0.9990168,0.00004855643,0.00006170988,0.000651354,0.0001115034,0.0001101187],"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":[0.00002755764,0.0003659443,0.01001933,0.000006873393,0.0000462947,0.000003687877,0.0001264533,0.8382605,0.0006314429,0.1219946,0.003088053,0.02542932],"study_design_scores_gemma":[0.0002254665,0.0002658956,0.04351835,0.00000434981,0.0000048248,0.00008432469,0.00002702466,0.9478441,0.00004542333,0.002527046,0.005251688,0.000201459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1013062,0.00005212625,0.8932039,0.00107719,0.0002059285,0.0003197482,0.000001824822,0.000385892,0.003447169],"genre_scores_gemma":[0.8883741,0.000002050452,0.1093835,0.0004301611,0.0002141199,0.00006854038,0.0000447754,0.00001107937,0.001471672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7870679,"threshold_uncertainty_score":0.4360572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00948284211519159,"score_gpt":0.2138572498916335,"score_spread":0.2043744077764419,"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."}}