{"id":"W2900613774","doi":"10.1109/tc.2018.2880742","title":"Efficient Mitchell’s Approximate Log Multipliers for Convolutional Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Erzincan Üniversitesi; University of Toronto","keywords":"Convolutional neural network; Computer science; Algorithm; Parallel computing; Arithmetic; Artificial intelligence; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004306663,0.0007997748,0.000407347,0.0005643783,0.0003874071,0.0008869426,0.001315466,0.0004373467,0.004167704],"category_scores_gemma":[0.002049202,0.0003089062,0.0003104998,0.0005618671,0.0004387987,0.001998954,0.0007882584,0.0008472747,0.0009065653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006441533,"about_ca_system_score_gemma":0.0009064202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001234801,"about_ca_topic_score_gemma":0.004193637,"domain_scores_codex":[0.9996505,0.0000698389,0.0000299942,0.00006024637,0.0001469972,0.00004239435],"domain_scores_gemma":[0.9996213,0.0001400891,0.00004763232,0.0000878167,0.00008770882,0.00001538673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005622496,0.0001425092,0.001075426,0.0002932817,0.00006687046,0.0003034634,0.0001460014,0.1498849,0.06491503,0.09102756,0.008868449,0.6827143],"study_design_scores_gemma":[0.00005657852,0.0004019908,0.0003696043,0.00005948408,0.00004180421,0.0003865581,0.00006152409,0.8892009,0.05088615,0.03953429,0.01896089,0.00004023118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03734715,0.0009477268,0.9544476,0.0001990118,0.0001277974,0.00006782118,0.00009091659,0.001404295,0.005367666],"genre_scores_gemma":[0.4091834,0.0006008327,0.5810432,0.0002015161,0.00008794054,0.000152483,0.0002476775,0.0001779853,0.008304972],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004167704,"threshold_uncertainty_score":0.01394236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0253079684981974,"score_gpt":0.2708273379042991,"score_spread":0.2455193694061017,"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."}}