{"id":"W4221036944","doi":"10.1109/tcsii.2022.3161005","title":"Variable-Precision Approximate Floating-Point Multiplier for Efficient Deep Learning Computation","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits & Systems II Express Briefs","topic":"Numerical Methods and Algorithms","field":"Computer Science","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); Computation; Exponent; Floating point; Adder; Mathematics; Multiplication (music); Algorithm; Computer science","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":[0.0003322534,0.0007313804,0.0003592606,0.0006397613,0.0003944613,0.0008156262,0.001286621,0.0004867128,0.01080567],"category_scores_gemma":[0.001020017,0.0002394774,0.0002997429,0.0007858995,0.0002985932,0.001317734,0.0004953197,0.0008100669,0.002719944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006599951,"about_ca_system_score_gemma":0.0007824047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001115907,"about_ca_topic_score_gemma":0.002415698,"domain_scores_codex":[0.9997532,0.00003138018,0.00002327711,0.00004721004,0.0001083614,0.00003665784],"domain_scores_gemma":[0.9997894,0.00004404742,0.0000227893,0.00003691823,0.00009625668,0.00001061661],"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":[0.0008219779,0.0001389422,0.001345568,0.0008220912,0.0001235186,0.000590187,0.0001859841,0.05435513,0.139749,0.08501761,0.02691097,0.6899391],"study_design_scores_gemma":[0.0001973195,0.001101476,0.00101312,0.0003062933,0.000121032,0.001401133,0.00009770024,0.6295509,0.1945378,0.03149749,0.1400717,0.0001040606],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0254564,0.002187816,0.954455,0.0004360032,0.000378033,0.000124375,0.0002977216,0.002674376,0.01399038],"genre_scores_gemma":[0.4838453,0.001546652,0.493808,0.0004804642,0.0001456936,0.0002823842,0.0006648243,0.0002065748,0.01901999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01080567,"threshold_uncertainty_score":0.03614855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02239759204039348,"score_gpt":0.2650750091429171,"score_spread":0.2426774171025236,"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."}}