{"id":"W2161294075","doi":"10.1109/icnn.1993.298622","title":"Acceleration of back propagation through initial weight pre-training with delta rule","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Backpropagation; Convergence (economics); Acceleration; Training (meteorology); Artificial neural network; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007821844,0.0002074979,0.0001886144,0.00006752411,0.0001251906,0.0002281994,0.0008544168,0.00008672682,0.0002824034],"category_scores_gemma":[0.000007807869,0.0001695567,0.00006124371,0.0003127797,0.00009059426,0.0009585141,0.00006943095,0.0002866941,0.00002739548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003291997,"about_ca_system_score_gemma":0.00002399679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001849293,"about_ca_topic_score_gemma":0.00002273969,"domain_scores_codex":[0.9983925,0.0000600894,0.0003871876,0.0004466866,0.0004499387,0.0002635469],"domain_scores_gemma":[0.998891,0.00009111118,0.0002885367,0.0003453485,0.0003147529,0.00006924359],"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":[0.0002034906,0.0005366555,0.0006614454,0.00002220997,0.000136637,0.00003408688,0.001565807,0.2957224,0.00384967,0.4627347,0.007365329,0.2271676],"study_design_scores_gemma":[0.0004007729,0.0002125668,0.0003962173,0.00007502594,0.000006090742,0.00002564849,0.00001103222,0.9942142,0.001982314,0.00195547,0.0005189509,0.0002016908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1197719,0.00003717788,0.8499989,0.005581388,0.001345021,0.0005818341,0.00001577436,0.0001721013,0.02249596],"genre_scores_gemma":[0.9938455,0.0000742116,0.004488138,0.0006327748,0.0005266329,0.00005984399,0.000032534,0.00001437488,0.0003260333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8740736,"threshold_uncertainty_score":0.6914322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1074472640247655,"score_gpt":0.3119474789161292,"score_spread":0.2045002148913637,"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."}}