{"id":"W4390097623","doi":"10.1109/tc.2023.3345163","title":"Learning the Error Features of Approximate Multipliers for Neural Network Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial neural network; Dropout (neural networks); Feature (linguistics); Mean squared error; Artificial intelligence; Machine learning; Algorithm; Mathematics; Statistics","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":[0.002085471,0.001117553,0.0007790368,0.001001279,0.0002519574,0.0008618503,0.0009396923,0.0006969958,0.0007790813],"category_scores_gemma":[0.01184788,0.0003503512,0.0004661302,0.0006418365,0.0005792737,0.001441683,0.0008628527,0.001064125,0.0002154334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006169415,"about_ca_system_score_gemma":0.0007116714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001616161,"about_ca_topic_score_gemma":0.001582001,"domain_scores_codex":[0.9990755,0.0001937713,0.0000742529,0.0001501663,0.0004480637,0.00005822677],"domain_scores_gemma":[0.9968148,0.001529092,0.0006256027,0.0002256142,0.0007504007,0.00005448982],"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":[0.0002429651,0.00008881502,0.005534851,0.0002330968,0.00006492222,0.00006624222,0.0000844638,0.754867,0.01196549,0.01225517,0.0009801924,0.2136167],"study_design_scores_gemma":[0.000003312028,0.00003797185,0.000379175,0.000009445625,0.000006449021,0.00001621571,0.000005117657,0.9946374,0.002239582,0.002396651,0.0002627675,0.000005870842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03954024,0.0003582262,0.9589225,0.0001012025,0.00002511586,0.00003646375,0.0000518405,0.0003327449,0.0006316999],"genre_scores_gemma":[0.75692,0.0005235009,0.2402175,0.000097285,0.0000650654,0.0002056427,0.0003061655,0.0001161083,0.001548782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002085471,"threshold_uncertainty_score":0.01102918,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01392849156788284,"score_gpt":0.2293794418490448,"score_spread":0.215450950281162,"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."}}