{"id":"W4285326164","doi":"10.1109/hpcc-dss-smartcity-dependsys53884.2021.00135","title":"Resource-Efficient DNN Training and Inference for Heterogeneous Edge Intelligence in 6G","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Wireless Communication Technologies","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Inference; Computer science; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Machine learning; Edge device; Artificial neural network; Edge computing; Deep learning; Cloud computing","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":[0.001089385,0.001351916,0.0008204237,0.0006015893,0.0005610334,0.001345068,0.001859525,0.001279027,0.002747918],"category_scores_gemma":[0.002428132,0.0004554507,0.0006337889,0.0007544046,0.000530234,0.002425099,0.001076776,0.002071014,0.000873483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001037496,"about_ca_system_score_gemma":0.001276406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01065556,"about_ca_topic_score_gemma":0.01896915,"domain_scores_codex":[0.9995988,0.00008469902,0.0000377438,0.0001091751,0.00008148735,0.00008804768],"domain_scores_gemma":[0.9995031,0.0002279448,0.00003328248,0.00005607858,0.0001517037,0.00002787015],"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":[0.0002448058,0.0001213052,0.004076983,0.0004780039,0.0001743769,0.0003091486,0.0001840912,0.4245037,0.006993262,0.02304561,0.01182425,0.5280443],"study_design_scores_gemma":[0.00001202874,0.00004297562,0.0005007514,0.00007290064,0.00005041418,0.00006599446,0.00005175748,0.9783685,0.003424641,0.01232222,0.005072991,0.00001482662],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02594259,0.00763212,0.9525642,0.00111186,0.0003950287,0.00009167421,0.0004683309,0.001444609,0.01034954],"genre_scores_gemma":[0.710738,0.008232792,0.265004,0.001599243,0.0004239829,0.000178614,0.002344883,0.0002779082,0.01120067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01065556,"threshold_uncertainty_score":0.02118707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04148214585213267,"score_gpt":0.2851048186770941,"score_spread":0.2436226728249615,"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."}}