{"id":"W2752214278","doi":"10.1109/wsom.2017.8020027","title":"Empirical evaluation of gradient methods for matrix learning vector quantization","year":2017,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Stochastic gradient descent; Gradient descent; Benchmark (surveying); Learning vector quantization; Quantization (signal processing); Artificial intelligence; Machine learning; Vector quantization; Algorithm; Artificial 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113667,0.00004447153,0.00007693371,0.00002431435,0.0002836578,0.00009603068,0.000373752,0.00002454932,0.000008616857],"category_scores_gemma":[0.0002137453,0.00003635184,0.00004408102,0.00006612863,0.00001959658,0.0001905368,0.00007784928,0.00003589332,0.000002924773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000140249,"about_ca_system_score_gemma":0.00002783446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009869343,"about_ca_topic_score_gemma":0.00000372247,"domain_scores_codex":[0.9993765,0.00009681992,0.000134348,0.0001664356,0.0001373389,0.0000886037],"domain_scores_gemma":[0.9991015,0.0001335594,0.0001587746,0.0003674614,0.0002108353,0.00002784796],"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":[0.000004596094,0.0000644325,0.002706938,0.00001338518,0.00001342879,4.382938e-8,0.0002019536,0.009881459,0.008238237,0.3546017,0.001220683,0.6230531],"study_design_scores_gemma":[0.0001692942,0.00003976582,0.01182234,0.000003959893,0.00001221329,5.336759e-7,0.000004468655,0.9696097,0.004646377,0.009681612,0.003961795,0.00004794277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01685921,0.00003814842,0.9804445,0.001624059,0.0001359017,0.0002811977,2.677672e-7,0.00003639243,0.000580345],"genre_scores_gemma":[0.6658021,0.00000424135,0.3339287,0.00001962157,0.00003518301,0.00004575307,0.000001986572,0.000002694425,0.0001596787],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9597282,"threshold_uncertainty_score":0.2181695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833703886838795,"score_gpt":0.5156207325397966,"score_spread":0.3322503438559171,"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."}}