{"id":"W4393388703","doi":"10.1007/s12530-024-09574-9","title":"Enhancing CNN structure and learning through NSGA-II-based multi-objective optimization","year":2024,"lang":"en","type":"article","venue":"Evolving Systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Computer science; Artificial intelligence; Multi-objective optimization; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001879202,0.00017063,0.0001663945,0.00008516735,0.0005435476,0.0004108731,0.0002674075,0.00007782327,0.000006265316],"category_scores_gemma":[0.00009592351,0.0001591109,0.00003383004,0.0006099524,0.00003287466,0.0008366118,0.0001494277,0.0003298659,0.000009313701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001131847,"about_ca_system_score_gemma":0.00005603854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005253407,"about_ca_topic_score_gemma":0.000009434515,"domain_scores_codex":[0.9986168,0.0001386405,0.0002395683,0.0005621352,0.0001943421,0.0002485229],"domain_scores_gemma":[0.9991153,0.000333294,0.00009321526,0.0003110807,0.00009386155,0.00005326175],"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":[9.596366e-7,0.000005930707,0.00008169215,0.00009776309,0.00001438387,0.000006300408,0.002452685,0.9862342,0.005128633,0.004841783,0.0001081993,0.001027428],"study_design_scores_gemma":[0.0001146799,0.0000360985,0.00009958729,0.0002763949,0.000007301461,0.0000210374,0.0001064269,0.9966384,0.001290041,0.0001962084,0.001036534,0.0001772863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00371603,0.003386483,0.9908137,0.0001570754,0.0006932554,0.0003460035,0.000002645495,0.0007167918,0.000168056],"genre_scores_gemma":[0.7548198,0.00001135191,0.2445252,0.00003821757,0.0001595315,0.00003869403,0.000006298581,0.00002129136,0.0003796728],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7511038,"threshold_uncertainty_score":0.6488353,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01261590665500422,"score_gpt":0.26042639883651,"score_spread":0.2478104921815058,"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."}}