{"id":"W2133796939","doi":"10.1109/icnn.1993.298720","title":"A new acceleration technique for the backpropagation algorithm","year":2002,"lang":"en","type":"article","venue":"IEEE International Conference on Neural Networks","topic":"Advanced Adaptive Filtering Techniques","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Orthogonalization; Backpropagation; Momentum (technical analysis); Acceleration; Algorithm; Convergence (economics); Orthogonality; Computer science; Mathematics; Gradient method; Artificial neural network; Artificial intelligence; Physics; Geometry","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":[0.00006748755,0.0001689753,0.00009992382,0.00006147719,0.00007607752,0.0001052852,0.0003528942,0.0000852618,0.0002567817],"category_scores_gemma":[0.00001576283,0.0001375057,0.00006062868,0.00008486267,0.00002457418,0.0002416106,0.00001808898,0.0002534499,0.00001167388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000874383,"about_ca_system_score_gemma":0.000004297205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005032152,"about_ca_topic_score_gemma":0.000004712514,"domain_scores_codex":[0.9992509,0.00001322809,0.0002006324,0.0001850765,0.0001693468,0.000180839],"domain_scores_gemma":[0.9994983,0.0001090007,0.00005251983,0.0001750043,0.0001207746,0.00004439385],"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":[0.00002706878,0.00001990608,0.00000637415,0.000006151075,0.00005229891,0.000003517781,0.00004731633,0.3613981,0.01677139,0.01120411,0.02165581,0.5888079],"study_design_scores_gemma":[0.0001435605,0.00007155345,0.0000350468,0.00003372776,0.000005028375,0.000008502886,0.000004117498,0.9802777,0.01378828,0.002345215,0.003136072,0.0001512396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001226046,0.00004628037,0.9948474,0.0007055486,0.001226149,0.0005996859,0.00001434319,0.0004277866,0.002010241],"genre_scores_gemma":[0.9514306,0.0002269361,0.04586281,0.0002007768,0.001028325,0.0004467905,0.00002453432,0.00004164792,0.0007375707],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.951308,"threshold_uncertainty_score":0.5607318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07931899361394502,"score_gpt":0.2954020287187492,"score_spread":0.2160830351048041,"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."}}