{"id":"W2897792138","doi":"10.1109/access.2018.2875376","title":"Impact of Approximate Multipliers on VGG Deep Learning Network","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Multiplication (music); Approximation error; Set (abstract data type); Algorithm; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001774357,0.0002104647,0.0002409811,0.0001204664,0.00009419829,0.00006482113,0.0004309741,0.0001014118,0.0001254799],"category_scores_gemma":[0.00001957715,0.0001828887,0.00009099657,0.0004123447,0.00007409431,0.0004044256,0.00003599016,0.0002471312,0.000159456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018682,"about_ca_system_score_gemma":0.0000146415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003160516,"about_ca_topic_score_gemma":0.000008252349,"domain_scores_codex":[0.99889,0.00002537069,0.0002403882,0.0001884215,0.0001877076,0.0004680682],"domain_scores_gemma":[0.9994003,0.00006555104,0.00006930502,0.0003154388,0.00005900319,0.00009046651],"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":[0.00005958718,0.00002423019,0.03372946,0.00005821358,0.0001178069,0.000004134125,0.0004692796,0.9474179,0.004787981,0.00001758769,0.00266781,0.01064601],"study_design_scores_gemma":[0.0009889206,0.0005150895,0.07308641,0.0001496856,0.00003502438,0.000005152352,0.00002184877,0.8756805,0.04803152,0.0001186169,0.0007875641,0.0005796512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9719948,0.00007610005,0.02043793,0.000002601438,0.00102591,0.0001765854,0.000002190241,0.0003641356,0.005919735],"genre_scores_gemma":[0.998597,0.00004131174,0.0006196517,0.00001615856,0.0005955921,0.00001583481,0.000003734626,0.00006662776,0.00004413514],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07173739,"threshold_uncertainty_score":0.7457986,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0158784648859035,"score_gpt":0.28145551504655,"score_spread":0.2655770501606465,"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."}}