{"id":"W4313006142","doi":"10.1109/ijcnn55064.2022.9892861","title":"Improving Neural Architecture Search by Mixing a FireFly algorithm with a Training Free Evaluation","year":2022,"lang":"en","type":"article","venue":"2022 International Joint Conference on Neural Networks (IJCNN)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de Recherche du Québec-Société et Culture; CHIST-ERA; Agence Nationale de la Recherche","keywords":"Firefly algorithm; Computer science; Metric (unit); Artificial neural network; Artificial intelligence; Machine learning; Algorithm; Baseline (sea); Architecture; Data mining; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004315159,0.002682048,0.002017576,0.002006606,0.0007594393,0.001180829,0.002780167,0.002277888,0.002460317],"category_scores_gemma":[0.008144253,0.0006512282,0.001205164,0.001160559,0.001045675,0.002273846,0.001599806,0.001788652,0.0007362093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001841666,"about_ca_system_score_gemma":0.002326882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006737082,"about_ca_topic_score_gemma":0.007426517,"domain_scores_codex":[0.9983846,0.0004933428,0.0001182449,0.0003361842,0.0004776558,0.0001899167],"domain_scores_gemma":[0.9974474,0.001111946,0.0002508278,0.0003893427,0.0006426134,0.0001579892],"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":[0.0002468324,0.0003466482,0.002832138,0.0001424118,0.0001817109,0.00008247255,0.00009701362,0.7668192,0.01111272,0.004482202,0.003350857,0.2103059],"study_design_scores_gemma":[0.00003392239,0.00009651202,0.0001709968,0.000008996256,0.0000175931,0.00001867484,0.000008660506,0.9966553,0.001699453,0.0008701499,0.0004116248,0.000008082501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0705789,0.0007851806,0.9209889,0.0003628151,0.0002308457,0.0002539165,0.00009202547,0.003194132,0.003513324],"genre_scores_gemma":[0.4407016,0.0002804708,0.5542951,0.0004033934,0.000115909,0.000384037,0.0003308761,0.0005170415,0.002971733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006737082,"threshold_uncertainty_score":0.02282101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04243884968605028,"score_gpt":0.2803751729514579,"score_spread":0.2379363232654076,"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."}}