{"id":"W2907361740","doi":"","title":"Quantization Error as a Metric for Dynamic Precision Scaling in Neural Net Training","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Rounding; Quantization (signal processing); Computer science; Scaling; Artificial neural network; Algorithm; Round-off error; Floating point; Metric (unit); Artificial intelligence; Mathematics","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":[0.00311943,0.001313147,0.0007235659,0.001038629,0.0008833791,0.002406918,0.002164801,0.001331087,0.00659774],"category_scores_gemma":[0.03961496,0.0004621978,0.0003681459,0.001641447,0.001439392,0.003663447,0.002847367,0.00293607,0.001553621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051056,"about_ca_system_score_gemma":0.00161135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001358651,"about_ca_topic_score_gemma":0.001839188,"domain_scores_codex":[0.996549,0.000687881,0.0005174469,0.0006069738,0.001418269,0.0002203646],"domain_scores_gemma":[0.9893396,0.003996839,0.0008771095,0.003861539,0.001758679,0.0001661335],"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":[0.001493652,0.0003057619,0.004321544,0.0005352452,0.00008983169,0.0003392402,0.0005616843,0.2434077,0.07140029,0.08231166,0.01706814,0.5781653],"study_design_scores_gemma":[0.000276999,0.0007799201,0.001696677,0.0004060486,0.00006860677,0.0005583782,0.0002162243,0.7162594,0.1513296,0.1064306,0.02183099,0.0001465607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07293218,0.00312849,0.9027843,0.001959545,0.0008393334,0.0002695169,0.0007990604,0.005517914,0.01176958],"genre_scores_gemma":[0.6448301,0.0007536242,0.3483799,0.0007556051,0.0001695494,0.0003902247,0.0005721751,0.0008513221,0.003297511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00659774,"threshold_uncertainty_score":0.0220716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236027287418837,"score_gpt":0.2618221371763817,"score_spread":0.138219408434498,"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."}}