{"id":"W3005746719","doi":"10.1109/newcas49341.2020.9159818","title":"An Energy-Efficient Accelerator Architecture with Serial Accumulation Dataflow for Deep CNNs","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dram; Computer science; Dataflow; Convolutional neural network; Computation; CAS latency; Latency (audio); Energy consumption; Convolution (computer science); Parallel computing; Embedded system; Computer hardware; Efficient energy use; Dataflow architecture; Architecture; Energy (signal processing); Artificial neural network; Artificial intelligence; Algorithm; Semiconductor memory","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001623793,0.0004944534,0.0003061809,0.0004269287,0.0003213216,0.0004560678,0.001386869,0.0003023355,0.004409242],"category_scores_gemma":[0.0002933767,0.000253042,0.0002913984,0.0005609962,0.0001698007,0.0008782386,0.0005213718,0.0004921654,0.0008503911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006219454,"about_ca_system_score_gemma":0.00108721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003353393,"about_ca_topic_score_gemma":0.006337859,"domain_scores_codex":[0.9998639,0.00001192889,0.00001169956,0.0000291573,0.00004904996,0.00003421464],"domain_scores_gemma":[0.9998703,0.00001791766,0.00001702835,0.00002569371,0.00005506483,0.00001401483],"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":[0.001329021,0.0006123166,0.005087959,0.0006733851,0.0002143577,0.0007426866,0.0001795583,0.1217163,0.2721857,0.02631728,0.04805088,0.5228906],"study_design_scores_gemma":[0.0001362049,0.000545598,0.001644052,0.00004756682,0.0001001764,0.000303495,0.0000406963,0.86687,0.09975526,0.004766282,0.02574598,0.0000446486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2786269,0.002824502,0.6795866,0.0008111937,0.0007574409,0.0002337,0.000819095,0.01387228,0.02246826],"genre_scores_gemma":[0.8076431,0.000607994,0.1768471,0.000303,0.00008560326,0.0001373477,0.001135345,0.0001603996,0.01308015],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004409242,"threshold_uncertainty_score":0.01475042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0536550752939182,"score_gpt":0.3169074449826198,"score_spread":0.2632523696887016,"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."}}