{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006080455,0.00008166405,0.0001145389,0.00006862573,0.00003046072,0.00001820796,0.0001583088,0.0000572361,0.00001049601],"category_scores_gemma":[0.0002151158,0.0000866082,0.00001654863,0.0001723798,0.00004632633,0.00003014477,0.0001079263,0.000114051,0.000002209007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003723572,"about_ca_system_score_gemma":0.00001103411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000105951,"about_ca_topic_score_gemma":0.00003723671,"domain_scores_codex":[0.9994951,0.000008990162,0.0001628584,0.0001310394,0.00004155578,0.0001604715],"domain_scores_gemma":[0.9993782,0.0002659257,0.00001320685,0.000296386,0.00002421682,0.00002208091],"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":[0.000001490076,0.00001227712,0.00006111389,0.00002879928,0.000004999765,0.000003531939,0.0007091535,0.5554475,0.002047943,0.007666733,0.00001043682,0.4340061],"study_design_scores_gemma":[0.0001160184,0.00002088913,0.00007831231,0.00005864001,0.000001703761,0.00001289982,0.002841227,0.7936279,0.1935463,0.002647876,0.006846301,0.0002019115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1667366,0.002712803,0.8284103,0.0001321293,0.00003167284,0.0001213494,0.000003259956,0.0004883378,0.001363539],"genre_scores_gemma":[0.967771,0.0003478609,0.0317464,0.00002569833,0.000004222494,0.00005271892,0.000003601708,0.00001334956,0.00003514426],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8010344,"threshold_uncertainty_score":0.353178,"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."}}