{"id":"W1568012513","doi":"10.1109/icnn.1995.488164","title":"A sparse matrix approach to neural network training","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Backpropagation; Artificial neural network; Training (meteorology); Artificial intelligence; Sparse matrix; Computation; Pattern recognition (psychology); Training set; Exploit; Matrix (chemical analysis); Multilayer perceptron; Machine learning; Speech recognition; Algorithm","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":[0.00007856434,0.00009256088,0.00009952969,0.00002589223,0.0001365313,0.0001430213,0.0006070776,0.0000254599,0.00004483898],"category_scores_gemma":[0.000002848956,0.00007687352,0.00004462198,0.0006300629,0.0000114811,0.0001612277,0.0001502064,0.00008829498,0.0002061947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007171676,"about_ca_system_score_gemma":0.000003203098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000536594,"about_ca_topic_score_gemma":0.00000193755,"domain_scores_codex":[0.9990794,0.00001812451,0.0001339727,0.0003079592,0.0001207737,0.0003397777],"domain_scores_gemma":[0.9993737,0.0000331742,0.00002434369,0.0004024971,0.00001515117,0.0001510885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001024931,0.00008832246,0.00007725624,0.000002745785,0.000006846137,0.000004334867,0.0008199947,0.1550422,0.00007385489,0.4942482,0.1921937,0.1574416],"study_design_scores_gemma":[0.00006864797,0.0000201214,0.0001948633,0.000002156934,0.000001548738,0.00002168619,0.00001424675,0.9602395,0.000007053482,0.001091443,0.03821504,0.0001237318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005160661,0.00009827439,0.9096435,0.004414539,0.0001633934,0.0002518241,4.009815e-7,0.0003655525,0.07990187],"genre_scores_gemma":[0.7674966,0.000004128605,0.2261611,0.002227078,0.000316155,0.00004659642,6.03971e-7,0.00000674835,0.003741004],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8051973,"threshold_uncertainty_score":0.3134811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07347713352903198,"score_gpt":0.2598918640087691,"score_spread":0.1864147304797371,"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."}}