{"id":"W2325049811","doi":"10.2514/6.2014-3144","title":"On Using Genetic Algorithm Optimized Activation Functions to Increase Neural Network Accuracy","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Sensor Technologies Research","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lockheed Martin (Canada)","funders":"","keywords":"Computer science; Artificial neural network; Genetic algorithm; Algorithm; Artificial intelligence; Machine learning","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":[0.00006264159,0.0001390922,0.0001320769,0.0001487555,0.0001112453,0.00003759701,0.0001585393,0.00007971047,0.0001124309],"category_scores_gemma":[0.0004930855,0.0001333201,0.00003370121,0.000449682,0.0000197275,0.0001238398,0.00006686041,0.0002331501,0.0001180617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338611,"about_ca_system_score_gemma":0.000005594686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003603323,"about_ca_topic_score_gemma":0.000001937769,"domain_scores_codex":[0.999085,0.00003218985,0.000149676,0.0001916935,0.0001685672,0.0003728634],"domain_scores_gemma":[0.9991407,0.0003368571,0.00001605331,0.0003628217,0.00004535001,0.00009819501],"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":[0.00001357422,0.00000621484,0.000006840346,0.00000301384,0.000007621956,0.000001004682,0.000003859651,0.8439135,0.004390487,0.00004622271,0.00105995,0.1505477],"study_design_scores_gemma":[0.0002730871,0.0000587951,0.0003638976,0.00001055826,0.00000403552,0.000003460917,0.00001994951,0.9938289,0.003227378,0.0003037172,0.001751687,0.0001545654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2591096,0.000006596296,0.7383727,0.00007345073,0.0001268136,0.0002143206,0.000001991977,0.0008184148,0.001276103],"genre_scores_gemma":[0.5441441,0.000007990992,0.4552213,0.0001441081,0.0001801494,0.00003319047,0.000008069766,0.00004816812,0.0002129502],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2850345,"threshold_uncertainty_score":0.5436637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02301762267903271,"score_gpt":0.2808723401686417,"score_spread":0.257854717489609,"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."}}