{"id":"W3173842498","doi":"","title":"Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update","year":2021,"lang":"en","type":"preprint","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Numerical Methods and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Semtech (Canada)","funders":"Nvidia; California Institute of Technology","keywords":"Computer science; Madam; Multiplicative function; Algorithm; Quantization (signal processing); Overhead (engineering); Convolutional neural network; Computer engineering; 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":[0.0005774843,0.0009546557,0.0005311713,0.000399153,0.000350311,0.001073419,0.001840817,0.0006652618,0.006457127],"category_scores_gemma":[0.002830946,0.0003941568,0.0003575611,0.0004302104,0.0005991868,0.001738455,0.0009636713,0.001428624,0.002317845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007124606,"about_ca_system_score_gemma":0.0009156251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001884841,"about_ca_topic_score_gemma":0.004579632,"domain_scores_codex":[0.9994622,0.00007018492,0.00004975727,0.0001632709,0.0002010668,0.0000534746],"domain_scores_gemma":[0.9994506,0.0001661256,0.00007510135,0.0001186295,0.0001576448,0.00003189805],"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":[0.0005877018,0.0002294977,0.002217161,0.0004346576,0.0000830041,0.0003208134,0.0002739387,0.2624943,0.07365811,0.02545984,0.01364472,0.6205963],"study_design_scores_gemma":[0.00005671768,0.0001646729,0.000313259,0.00004416588,0.00002678663,0.0001288064,0.00002794895,0.9543554,0.02956297,0.005926133,0.009371123,0.00002199952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03069945,0.0007486203,0.954603,0.0004184869,0.0002456049,0.00009371466,0.00009692621,0.005825525,0.007268665],"genre_scores_gemma":[0.5215585,0.0004496871,0.4660311,0.0006997476,0.0001197088,0.0002905126,0.0003259863,0.0005052632,0.01001948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006457127,"threshold_uncertainty_score":0.0216012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03206347963469536,"score_gpt":0.304197529823886,"score_spread":0.2721340501891907,"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."}}