{"id":"W4281691647","doi":"10.1016/j.comcom.2022.05.035","title":"A federated calibration scheme for convolutional neural networks: Models, applications and challenges","year":2022,"lang":"en","type":"article","venue":"Computer Communications","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"King Saud University","keywords":"Computer science; Convolutional neural network; Deep learning; Artificial intelligence; Network architecture; Artificial neural network; Path (computing); Cluster analysis; Pattern recognition (psychology); Machine learning; Computer network","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004632952,0.0008349574,0.0008912188,0.0006402807,0.0007384359,0.001935826,0.002723976,0.002192639,0.002698384],"category_scores_gemma":[0.009703645,0.0006190579,0.0005909306,0.001042361,0.000957887,0.003982733,0.002851327,0.00370286,0.001082898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001503095,"about_ca_system_score_gemma":0.002577818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004828779,"about_ca_topic_score_gemma":0.004657888,"domain_scores_codex":[0.9985681,0.0005083663,0.00006194657,0.0003071034,0.0004570214,0.000097608],"domain_scores_gemma":[0.9969401,0.0004801698,0.0002163347,0.001067189,0.001192911,0.0001033159],"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":[0.0003273947,0.000135167,0.001763905,0.0001125693,0.0001427236,0.00008154332,0.0001260738,0.5266511,0.01272265,0.07838039,0.005093637,0.3744628],"study_design_scores_gemma":[0.000009229552,0.00002232514,0.0001602319,0.00002117569,0.0000108083,0.00004052928,0.000007164618,0.9783805,0.004296347,0.01543272,0.001604741,0.0000141832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006739069,0.0002499343,0.9911938,0.0002759699,0.00004658035,0.00002132132,0.00004811565,0.0005972842,0.0008280071],"genre_scores_gemma":[0.4429628,0.0005480245,0.5504146,0.0003492645,0.0001047539,0.0001056442,0.0003305307,0.0002675979,0.004916723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004828779,"threshold_uncertainty_score":0.02450168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09128292449671148,"score_gpt":0.2811332553182015,"score_spread":0.18985033082149,"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."}}