{"id":"W4400776767","doi":"10.32913/mic-ict-research-vn.v2024.n1.1267","title":"Omni-Dimensional Adaptation for MobileNetV3 using Bayesian Hyperparameter Tuning","year":2024,"lang":"en","type":"article","venue":"Journal on Information Technologies & Communications","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Hyperparameter; Convolution (computer science); Computer science; Artificial intelligence; Bayesian probability; Feature (linguistics); Representation (politics); Pattern recognition (psychology); Channel (broadcasting); Bayesian optimization; Convolutional neural network; Bayesian inference; Machine learning; Algorithm; Artificial neural network","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005344013,0.0001713007,0.0002253002,0.001083776,0.0005820821,0.000306803,0.0004703759,0.0002052634,0.00002675969],"category_scores_gemma":[0.001100194,0.0001490093,0.0001821766,0.0005981523,0.0001493837,0.001131939,0.0001845692,0.0007763559,0.00005707246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006066553,"about_ca_system_score_gemma":0.0004061102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001235749,"about_ca_topic_score_gemma":0.000002575098,"domain_scores_codex":[0.9985943,0.00004062025,0.000689769,0.0001202025,0.0003225334,0.0002325926],"domain_scores_gemma":[0.9974037,0.0009142834,0.0002652242,0.0009530474,0.0004022627,0.00006153007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002745983,0.0004771211,0.0003047044,0.0005655139,0.0005412311,0.00001761063,0.002884148,0.04793267,0.004032071,0.03447872,0.05165465,0.856837],"study_design_scores_gemma":[0.0005108179,0.0002954629,0.0001066981,0.0008724497,0.0001272498,0.0003727859,0.001487891,0.6425766,0.0007822784,0.00285968,0.3498424,0.0001656446],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08407561,0.004692544,0.5887336,0.3118208,0.001561771,0.002973248,0.0001300954,0.004619138,0.001393282],"genre_scores_gemma":[0.8167968,0.0006846847,0.177454,0.004681277,0.00005348755,0.0001529298,0.000109754,0.00002696142,0.00004006239],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8566713,"threshold_uncertainty_score":0.6076424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07853628971206912,"score_gpt":0.3635132981727131,"score_spread":0.2849770084606439,"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."}}