{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003973451,0.0002325637,0.0002177369,0.0001859009,0.0005391367,0.0001696683,0.0006516474,0.0001021561,0.000009765144],"category_scores_gemma":[0.000004710762,0.0002265059,0.000224964,0.0003694537,0.0002103591,0.000132026,0.000006588418,0.0002192297,0.00002775401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008602358,"about_ca_system_score_gemma":0.0000484213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001032841,"about_ca_topic_score_gemma":0.00000199244,"domain_scores_codex":[0.9983019,0.0001010796,0.0002840024,0.0005586741,0.0002570846,0.0004973147],"domain_scores_gemma":[0.9986726,0.0004519097,0.00007951323,0.0004580575,0.0001846028,0.0001533105],"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":[0.0001163603,0.0001601282,0.000001319282,0.000009735472,0.0000468801,0.000005227647,0.0003012757,0.8859658,0.0006220561,0.0006959289,0.0009307953,0.1111446],"study_design_scores_gemma":[0.001282817,0.0002885701,0.00002920802,0.00002143974,0.00001725805,0.00002627731,0.000007384154,0.992027,0.005544738,0.0001813845,0.0003196528,0.0002543019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002785749,0.0000258283,0.9906004,0.0003770034,0.00543057,0.0003854026,0.000009451645,0.0002955323,0.0000900496],"genre_scores_gemma":[0.6487516,0.000001281189,0.3499131,0.0009659402,0.0002254756,0.00003580255,0.000001647365,0.00001646074,0.00008866336],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6459659,"threshold_uncertainty_score":0.9236643,"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."}}