{"id":"W3111591377","doi":"10.1109/smc42975.2020.9283092","title":"Power and Performance Analysis of Deep Neural Networks for Energy-aware Heterogeneous Systems","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Convolution (computer science); Artificial neural network; CUDA; Symmetric multiprocessor system; Computer architecture; Power (physics); Supercomputer; Efficient energy use; Convolutional neural network; Embedded system; Green computing; Electrical efficiency; Energy (signal processing); Computer engineering; Artificial intelligence; Parallel computing; Operating system; Cloud computing; Engineering; Electrical engineering","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":[0.000384115,0.0006073169,0.0003448586,0.0004967263,0.0002777981,0.0004217674,0.000637852,0.0002069108,0.002847672],"category_scores_gemma":[0.001548614,0.0001684631,0.0002657046,0.0006510213,0.000257018,0.001080874,0.0002974192,0.0003429872,0.0002616983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009626546,"about_ca_system_score_gemma":0.0004112814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004383498,"about_ca_topic_score_gemma":0.004359616,"domain_scores_codex":[0.9997163,0.00004332382,0.00001567601,0.00005855601,0.00009651832,0.0000695389],"domain_scores_gemma":[0.9995126,0.0002232969,0.00004816333,0.00006246664,0.0001296836,0.00002394359],"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":[0.0009515056,0.0003540279,0.00920552,0.0002355683,0.0001048641,0.0003605944,0.000133702,0.8341572,0.05161598,0.004512721,0.003338234,0.0950301],"study_design_scores_gemma":[0.000006351625,0.0001075764,0.002505165,0.000004986341,0.00001460118,0.00002038522,0.00003287291,0.9830413,0.01311761,0.000760915,0.0003821586,0.000005999003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9488465,0.000572412,0.04184278,0.0003017384,0.00004495569,0.00003818397,0.0003372519,0.0006338106,0.007382463],"genre_scores_gemma":[0.9959524,0.00008885307,0.002824363,0.00001938322,0.000005482215,0.00001781663,0.0001290132,0.00006008081,0.0009026913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004383498,"threshold_uncertainty_score":0.009526432,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01393058133394705,"score_gpt":0.2326733664327306,"score_spread":0.2187427850987836,"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."}}