{"id":"W2105686536","doi":"10.1109/icnn.1994.374492","title":"Training artificial neural networks using variable precision incremental communication","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Variable (mathematics); Computer science; Artificial neural network; Scheme (mathematics); Convergence (economics); Node (physics); Feed forward; Computation; Degree (music); Artificial intelligence; Computer engineering; Algorithm; Mathematics; Control engineering","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":[0.0006596454,0.0003341607,0.0003767643,0.0002990442,0.0002934064,0.0004412064,0.001018311,0.0005108923,0.00114579],"category_scores_gemma":[0.003214266,0.0001998196,0.0002126334,0.0004296934,0.0005039652,0.0009989548,0.0006670636,0.0007218472,0.0001575947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003906983,"about_ca_system_score_gemma":0.0005129759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002507847,"about_ca_topic_score_gemma":0.002617388,"domain_scores_codex":[0.9997308,0.00008358066,0.00001836892,0.00003393182,0.00009877423,0.00003454466],"domain_scores_gemma":[0.9990222,0.0005806272,0.00009314858,0.0001300816,0.0001543333,0.00001960785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001780044,0.00004463883,0.0007118293,0.00006694221,0.00002938195,0.00008151308,0.000159335,0.8321114,0.01128581,0.0123483,0.0006850954,0.1422978],"study_design_scores_gemma":[0.00001519685,0.00004940925,0.0001053058,0.000004787847,0.00000627114,0.00001576283,0.000007090009,0.9936772,0.003448034,0.002165504,0.0005011777,0.000004381863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08519543,0.0002193066,0.9106691,0.0001623717,0.00005567455,0.00004506448,0.00001827106,0.0006991939,0.002935634],"genre_scores_gemma":[0.8117101,0.0001690652,0.1864515,0.00006717263,0.00003251846,0.0001023371,0.00004627304,0.00003180303,0.001389202],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002507847,"threshold_uncertainty_score":0.004986525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1123116579925676,"score_gpt":0.2866832201117676,"score_spread":0.1743715621192,"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."}}