{"id":"W2137939963","doi":"10.1109/ijcnn.1991.155308","title":"Mean-variance backpropagation: a connectionist learning algorithm with a selective attention mechanism","year":2002,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Backpropagation; Artificial intelligence; Computer science; Connectionism; Rprop; Artificial neural network; Algorithm; Variance (accounting); Mean squared error; Machine learning; Asymptote; Gradient descent; Pattern recognition (psychology); Mathematics; Statistics; Types of artificial neural networks; Recurrent neural network","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":[0.0008053554,0.001003578,0.0008418618,0.0007623916,0.0004277354,0.0008832087,0.002089736,0.001540547,0.003043775],"category_scores_gemma":[0.002311224,0.0005402958,0.0005833346,0.001028763,0.0005963919,0.00158253,0.0008124041,0.001538412,0.001389047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006050103,"about_ca_system_score_gemma":0.0008871357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003864564,"about_ca_topic_score_gemma":0.005363345,"domain_scores_codex":[0.9995689,0.00008099078,0.0000262383,0.00008847196,0.0002017848,0.00003366405],"domain_scores_gemma":[0.9994736,0.0001922919,0.00004300429,0.00006773799,0.0001971212,0.00002632723],"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":[0.0001966065,0.0001439934,0.0006381531,0.0002128879,0.0003115189,0.0001764896,0.00005887748,0.2210755,0.03057422,0.01901987,0.01343203,0.7141598],"study_design_scores_gemma":[0.00003199779,0.00003531411,0.0002387225,0.00001255248,0.00003231137,0.00009513837,0.000002352273,0.9772585,0.008207587,0.007451256,0.006612622,0.00002170899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002446442,0.0002569787,0.9942102,0.0001412978,0.0001115254,0.00002928768,0.00003103098,0.001698462,0.001074758],"genre_scores_gemma":[0.1013701,0.0006135611,0.8888834,0.0002912049,0.0002017402,0.0001596857,0.0001941473,0.0004272877,0.007858924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003864564,"threshold_uncertainty_score":0.01018244,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01328137695758021,"score_gpt":0.2214042596374503,"score_spread":0.2081228826798701,"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."}}