{"id":"W2806244818","doi":"10.1109/access.2018.2842202","title":"Evolving Convolutional Neural Network and Its Application in Fine-Grained Visual Categorization","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Categorization; Classifier (UML); Pattern recognition (psychology); Class (philosophy); Deep neural networks; Machine learning; Deep learning","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":[0.0001588154,0.00008985971,0.00009431817,0.00007799528,0.0001124179,0.0001340726,0.0003953936,0.00004795997,0.000003995658],"category_scores_gemma":[0.00005210417,0.00008893696,0.0000133348,0.0006301761,0.00004040435,0.001691596,0.0001492538,0.00007966119,0.000006832904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003408598,"about_ca_system_score_gemma":0.00002740853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002895816,"about_ca_topic_score_gemma":0.00003844982,"domain_scores_codex":[0.9991798,0.00003311714,0.0001700138,0.0002872361,0.0001325425,0.000197221],"domain_scores_gemma":[0.9995126,0.00005722875,0.00008028634,0.0001446587,0.00016378,0.00004147316],"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":[0.0001695371,0.0003442823,0.1218786,0.0001480617,0.00003795932,0.00003697712,0.001073539,0.003468342,0.08547185,0.1720234,0.008114574,0.6072329],"study_design_scores_gemma":[0.0002678623,0.00009539284,0.04280278,0.00001975849,0.000002519944,0.000007783043,0.000001688584,0.9016464,0.03595242,0.01849441,0.0005178413,0.000191085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06367978,0.0002067764,0.935243,0.0001890398,0.000173951,0.0002104493,6.45524e-7,0.0001506059,0.0001457597],"genre_scores_gemma":[0.9956304,0.00001987914,0.003693472,0.0002289711,0.0003548764,0.00003138927,0.000005429665,0.000006452563,0.00002907572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9319507,"threshold_uncertainty_score":0.3626744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02339973708229362,"score_gpt":0.3365860451156487,"score_spread":0.313186308033355,"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."}}