{"id":"W4381515053","doi":"10.1007/s11390-023-2548-8","title":"Approximate Processing Element Design and Analysis for the Implementation of CNN Accelerators","year":2023,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Low-power high-performance VLSI design","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Adder; Multiplication (music); Overhead (engineering); Convolutional neural network; Rounding; Lookup table; Computation; Floating point; Algorithm; Dot product; Computer engineering; Computer hardware; Parallel computing; Artificial intelligence; Latency (audio); 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":[0.001107229,0.00005972518,0.000144658,0.001021675,0.0001195125,0.00006313746,0.0002417413,0.00002761524,0.000001073769],"category_scores_gemma":[0.000007475501,0.00003925463,0.00001892413,0.002488171,0.0001614235,0.0002991748,0.00005366988,0.00006477453,1.520637e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000220823,"about_ca_system_score_gemma":0.0000582462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.948577e-7,"about_ca_topic_score_gemma":5.889458e-7,"domain_scores_codex":[0.9993141,0.000005238005,0.000245241,0.00008105556,0.0001921402,0.0001621901],"domain_scores_gemma":[0.9995151,0.00004337687,0.0001175521,0.000079643,0.0002202567,0.00002410488],"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":[0.000008809976,0.00001202245,0.01295919,0.00009733294,0.0002970915,0.00000364226,0.001106374,0.03625215,0.02487798,0.0006481785,0.0004433984,0.9232938],"study_design_scores_gemma":[0.0003112383,0.0002172539,0.008377361,0.00001394889,0.0001075003,0.0000164556,0.0003129831,0.9261914,0.06358773,0.0006295082,0.0001701975,0.00006441706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4139161,0.0001607343,0.5854854,0.0002515922,0.00006459036,0.00009334732,4.062792e-7,0.00002703234,7.621704e-7],"genre_scores_gemma":[0.9635875,0.0001771871,0.03619127,0.00001223417,0.00002040017,0.00000689805,1.54876e-7,0.000003875429,5.327251e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9232294,"threshold_uncertainty_score":0.1600757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01712385666464078,"score_gpt":0.2716650361650627,"score_spread":0.2545411795004219,"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."}}