{"id":"W2943422048","doi":"10.1109/iscas.2019.8701880","title":"Energy-Efficient Approximate MAC Unit","year":2019,"lang":"en","type":"article","venue":"","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Energy consumption; Convolutional neural network; Reduction (mathematics); Power (physics); Energy (signal processing); Unit (ring theory); Smoothing; Power consumption; Efficient energy use; Architecture; Artificial intelligence; Mathematics; Electrical engineering; Engineering","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":[0.0002102871,0.0004333837,0.0004615647,0.0005070043,0.0003934357,0.0009219794,0.001349056,0.0003803507,0.00528594],"category_scores_gemma":[0.0007234349,0.000218384,0.0002838649,0.000453325,0.0002897301,0.001327857,0.0004560128,0.000392275,0.0008763854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005736357,"about_ca_system_score_gemma":0.0008151453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001437901,"about_ca_topic_score_gemma":0.002779307,"domain_scores_codex":[0.9996915,0.00003909385,0.00002637494,0.00006198546,0.0001400527,0.00004109582],"domain_scores_gemma":[0.9995767,0.00006213399,0.00005964488,0.0001371448,0.0001485295,0.00001581994],"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":[0.001130401,0.0001417566,0.001785751,0.0003907533,0.0001376795,0.0003572247,0.0002472862,0.1188391,0.2274243,0.04166034,0.009258131,0.5986273],"study_design_scores_gemma":[0.00006115687,0.0007225829,0.001450271,0.00003548715,0.0001202779,0.0008281674,0.00006648995,0.8134224,0.1426713,0.00764621,0.03292326,0.00005236115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1393963,0.001571054,0.8388372,0.0003390238,0.000182887,0.0001207805,0.0001836126,0.004354337,0.01501476],"genre_scores_gemma":[0.7527789,0.0002622174,0.2359681,0.0002154725,0.00007451113,0.00007979763,0.000204744,0.00008677661,0.01032946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00528594,"threshold_uncertainty_score":0.01768327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006008932852871851,"score_gpt":0.1748830199459054,"score_spread":0.1688740870930335,"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."}}