{"id":"W4312744061","doi":"10.1109/jetcas.2022.3231642","title":"Efficient Approximate Posit Multipliers for Deep Learning Computation","year":2022,"lang":"en","type":"article","venue":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Ocean University of China; University of Saskatchewan","keywords":"Multiplier (economics); Adder; Computation; Logarithm; Fraction (chemistry); Computer science; Arithmetic; Artificial neural network; Deep learning; Mathematics; Algorithm; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004190383,0.0001321591,0.000203761,0.0002497461,0.0004160164,0.0001037311,0.00006193046,0.00004689461,0.000001441515],"category_scores_gemma":[0.00001266931,0.0001304198,0.00002393112,0.0002423025,0.00001047013,0.00004101975,0.000006957836,0.000479465,3.041228e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001427044,"about_ca_system_score_gemma":0.00001004326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003509324,"about_ca_topic_score_gemma":0.000001226579,"domain_scores_codex":[0.9990231,0.00007160736,0.0003126689,0.0001341123,0.000193556,0.0002648949],"domain_scores_gemma":[0.9997047,0.00006674758,0.00006209692,0.00004522266,0.00005084405,0.00007034227],"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":[0.000006255701,0.00001409338,0.0007784417,0.0001247143,0.00003104726,0.000007970705,0.001937504,0.9826106,0.001982666,0.00005958619,0.00007073915,0.01237641],"study_design_scores_gemma":[0.000732706,0.0001465051,0.0008888404,0.00005813644,0.00001030169,0.0001301898,0.0004785402,0.99571,0.00008522697,0.00001426196,0.001580687,0.0001646449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9629765,0.001449145,0.03333285,0.00002042452,0.001716046,0.0002437774,0.000002661959,0.00009377591,0.0001648382],"genre_scores_gemma":[0.9994617,0.0001520852,0.00006667743,0.00001074727,0.0001897907,0.0000303818,0.000004863341,0.00002684847,0.00005693062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0364852,"threshold_uncertainty_score":0.5318366,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01301307002698404,"score_gpt":0.2266748595530422,"score_spread":0.2136617895260581,"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."}}