{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001465817,0.000156807,0.0001556098,0.000127461,0.0002945802,0.00002844588,0.0002421415,0.0000626927,0.000003765546],"category_scores_gemma":[0.000001027662,0.0001316547,0.0001270521,0.0005956974,0.00005959834,0.00008601105,0.000001459997,0.0002751821,0.00002203082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003515793,"about_ca_system_score_gemma":0.000009700222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000374717,"about_ca_topic_score_gemma":0.000005123565,"domain_scores_codex":[0.9991732,0.00002328193,0.0001964597,0.0001670878,0.0001296411,0.0003103831],"domain_scores_gemma":[0.9993327,0.000307153,0.00003603657,0.0002463551,0.00003030884,0.00004739271],"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":[0.00001462507,0.00001159383,0.000006409361,0.00005252113,0.00006342882,2.985762e-7,0.0004075016,0.9554614,0.0005894623,0.00003045355,0.002586467,0.04077588],"study_design_scores_gemma":[0.0003405484,0.00006432326,0.0002170348,0.00002482699,0.00003188253,0.000002879501,0.00011199,0.993013,0.003517191,0.00002797775,0.002499759,0.0001485904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01768765,0.00003259255,0.9792845,0.0001308824,0.001219423,0.0007191126,0.00001826718,0.0008225078,0.0000851281],"genre_scores_gemma":[0.9927797,0.00003726624,0.006364564,0.00004590266,0.0001205042,0.0004647856,0.00001009447,0.00005197383,0.0001252178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9750921,"threshold_uncertainty_score":0.5368724,"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."}}