{"id":"W3027275906","doi":"10.3934/cpaa.2020180","title":"Quantitative convergence analysis of kernel based large-margin unified machines","year":2020,"lang":"en","type":"article","venue":"Communications on Pure &amp Applied Analysis","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reproducing kernel Hilbert space; Support vector machine; Hilbert space; Margin (machine learning); Computer science; Binary classification; Kernel method; Convergence (economics); Dimension (graph theory); Kernel (algebra); A priori and a posteriori; Binary number; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Margin classifier; Projection (relational algebra); Algorithm; Machine learning; Mathematics; Discrete mathematics; Mathematical analysis","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":[0.0106914,0.00124217,0.00137038,0.002273389,0.0007022892,0.002127115,0.002060002,0.001590289,0.00270596],"category_scores_gemma":[0.04607741,0.0005690796,0.0009553345,0.0009767351,0.003393531,0.004626094,0.003247483,0.002723372,0.0005827133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002175696,"about_ca_system_score_gemma":0.001112679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001059713,"about_ca_topic_score_gemma":0.0005263893,"domain_scores_codex":[0.9969561,0.001622036,0.0001113271,0.0003375653,0.0007613642,0.0002116332],"domain_scores_gemma":[0.9759668,0.01629475,0.001824978,0.001306062,0.003785108,0.000822339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001594825,0.00006385733,0.001551706,0.0003671218,0.00007520472,0.0001317942,0.0003362857,0.2530279,0.003537536,0.7154902,0.0025232,0.02273566],"study_design_scores_gemma":[0.000004957585,0.0000348486,0.0003228074,0.0000332691,0.000007598886,0.00003284847,0.0000248447,0.9230656,0.000581469,0.075388,0.0004886927,0.00001499861],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04250475,0.001910755,0.948897,0.0007777314,0.00008765941,0.00005382446,0.00007143235,0.0002711562,0.005425758],"genre_scores_gemma":[0.8386635,0.001872753,0.1489971,0.0004446351,0.0003367763,0.0003438072,0.0003778852,0.0004574154,0.008506064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0106914,"threshold_uncertainty_score":0.05654222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04423434255244192,"score_gpt":0.3163046946359783,"score_spread":0.2720703520835364,"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."}}