{"id":"W4312763065","doi":"10.1109/icpr56361.2022.9956269","title":"Analysis of Different Deep Learning Architectures to Learn Generalised Classifier Stacking on Riemannian and Grassmann Manifolds","year":2022,"lang":"en","type":"article","venue":"2022 26th International Conference on Pattern Recognition (ICPR)","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Classifier (UML); Euclidean geometry; Artificial intelligence; Convolutional neural network; Pairwise comparison; Pattern recognition (psychology); Mathematics; Deep learning; Lying; Stacking; Riemannian geometry; Artificial neural network; Computer science; Pure mathematics; Geometry; Physics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003530081,0.0002327524,0.0003760307,0.0008575907,0.0002532405,0.0000931275,0.0002893994,0.0000630374,0.01365672],"category_scores_gemma":[0.0001901069,0.0002098749,0.0001807364,0.0004000449,0.00003221896,0.00003731239,0.0002282866,0.0005112684,0.00002539783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000111828,"about_ca_system_score_gemma":0.00001460505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005117832,"about_ca_topic_score_gemma":0.0001090701,"domain_scores_codex":[0.9977033,0.0003507771,0.0004826668,0.0005027961,0.0007370229,0.0002234384],"domain_scores_gemma":[0.9988468,0.0003205998,0.0003374024,0.0002105219,0.000173329,0.0001113444],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001342598,0.003993238,0.1854182,0.0002207826,0.00662382,0.0002115559,0.005150543,0.0152407,0.01364045,0.1218562,0.003562012,0.6427398],"study_design_scores_gemma":[0.004073937,0.004428769,0.6229219,0.0003718932,0.001719509,0.00004066691,0.005501684,0.2753406,0.00403111,0.07405192,0.005176433,0.002341666],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9687966,0.000005307158,0.02263104,0.001421937,0.0002575661,0.0002648779,0.0004004572,0.00005713476,0.006165046],"genre_scores_gemma":[0.9966982,0.0000149692,0.0004802265,0.00102937,0.00007903634,0.0001507567,0.0005455065,0.00002329085,0.0009786348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6403982,"threshold_uncertainty_score":0.9872449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09741439662480494,"score_gpt":0.3205815274068795,"score_spread":0.2231671307820745,"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."}}