{"id":"W2034877773","doi":"10.1016/j.neunet.2012.12.009","title":"A class of finite-time dual neural networks for solving quadratic programming problems and its -winners-take-all application","year":2013,"lang":"en","type":"article","venue":"Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":159,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Artificial neural network; Quadratic programming; Computer science; Convergence (economics); Mathematical optimization; Class (philosophy); Quadratic equation; Activation function; Function (biology); Recurrent neural network; Stability (learning theory); Limiting; Property (philosophy); Dual (grammatical number); Mathematics; Artificial intelligence; Machine learning","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":[0.00194988,0.001183454,0.001353891,0.0007662683,0.0006690351,0.001371421,0.002229262,0.00144824,0.003187591],"category_scores_gemma":[0.004474268,0.0005133364,0.0009353239,0.0009798201,0.001061541,0.00170315,0.001926063,0.003058603,0.000390129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008726627,"about_ca_system_score_gemma":0.001222004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001739602,"about_ca_topic_score_gemma":0.002156541,"domain_scores_codex":[0.9994088,0.0002317922,0.00003151991,0.0001090716,0.0001464435,0.00007227279],"domain_scores_gemma":[0.999105,0.000413139,0.00009542175,0.00008059776,0.0002044707,0.0001013135],"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":[0.0003243279,0.0002781847,0.0007918201,0.000346084,0.0001558259,0.0001240126,0.00009991391,0.413777,0.003042768,0.3839589,0.007508147,0.1895929],"study_design_scores_gemma":[0.00002169161,0.00007269677,0.00009148791,0.00001945631,0.00001493462,0.00004136216,0.00001135854,0.9272487,0.0003296897,0.07018252,0.001956546,0.000009626639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02426515,0.002129737,0.9585652,0.000585859,0.0003079155,0.00007098616,0.0001079956,0.0002252474,0.01374197],"genre_scores_gemma":[0.675988,0.002637361,0.2991209,0.0005435646,0.0005075807,0.0003446041,0.0003717483,0.0002533955,0.02023282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003187591,"threshold_uncertainty_score":0.01066357,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02072694984196465,"score_gpt":0.2387100501315881,"score_spread":0.2179831002896234,"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."}}