{"id":"W2971946864","doi":"10.1109/tc.2019.2936192","title":"New Flexible Multiple-Precision Multiply-Accumulate Unit for Deep Neural Network Training and Inference","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Floating-point unit; Computer science; Floating point; IEEE floating point; Binary number; Unit (ring theory); Artificial neural network; 16-bit; Single-precision floating-point format; Algorithm; Computer hardware; Overhead (engineering); Exponent; Arithmetic; Control unit; Parallel computing; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006635711,0.001314767,0.0006790535,0.001378965,0.0007811505,0.001353899,0.00295911,0.000694119,0.01010667],"category_scores_gemma":[0.002159658,0.0005077791,0.0005002946,0.001179582,0.0005012574,0.002507249,0.001221508,0.001287824,0.002615752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009733676,"about_ca_system_score_gemma":0.001528963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003082427,"about_ca_topic_score_gemma":0.005545321,"domain_scores_codex":[0.9992029,0.00007259219,0.00009337,0.0001732134,0.0003591126,0.00009877387],"domain_scores_gemma":[0.9991645,0.0001358984,0.00008442856,0.0001767955,0.0003899174,0.00004841001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001166476,0.0001750265,0.001738099,0.0006287102,0.0001668972,0.0004738838,0.0002214686,0.02600223,0.09192011,0.03033528,0.02075784,0.8264139],"study_design_scores_gemma":[0.0001912763,0.0009008697,0.001289677,0.0001722626,0.0002395057,0.001023847,0.00008421862,0.658649,0.2418276,0.01197,0.08350144,0.000150273],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02279138,0.001693279,0.957388,0.0003103605,0.0005273453,0.0002490908,0.0003415542,0.008555706,0.008143212],"genre_scores_gemma":[0.3884953,0.001007031,0.5929577,0.0006098801,0.0002948088,0.0004564414,0.0009963888,0.0003556597,0.01482676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01010667,"threshold_uncertainty_score":0.0338102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05346103363208157,"score_gpt":0.3028072657203022,"score_spread":0.2493462320882206,"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."}}