{"id":"W4378697064","doi":"10.1109/jiot.2023.3280746","title":"Stochastic Cumulative DNN Inference With RL-Aided Adaptive IoT Device-Edge Collaboration","year":2023,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Age of Information Optimization","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); Toronto Metropolitan University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Computer science; Inference; Edge device; Edge computing; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Artificial neural network; Machine learning; Distributed computing; Cloud computing","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006816369,0.0001705684,0.0002171297,0.0004209775,0.0001120193,0.0003532292,0.0007609074,0.00007297387,0.00002724514],"category_scores_gemma":[0.0003358369,0.0001408177,0.00005022417,0.0009695244,0.00007184131,0.002931021,0.0001171683,0.0003214565,0.00009807601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001686202,"about_ca_system_score_gemma":0.0002917851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002686603,"about_ca_topic_score_gemma":0.000009483681,"domain_scores_codex":[0.9983044,0.00009721842,0.0005622936,0.0001835263,0.0006182934,0.0002342262],"domain_scores_gemma":[0.997377,0.0002742965,0.0008701049,0.0002090757,0.001157393,0.0001121637],"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":[0.0001837771,0.00005624805,0.0001759657,0.00003010534,0.0001620992,0.0000436864,0.05649527,0.9172772,0.0006529817,0.01085048,0.005087782,0.00898441],"study_design_scores_gemma":[0.0005431784,0.0003826421,0.0003471342,0.0003047951,0.00001234914,0.00008364609,0.0006882254,0.9925395,0.003441674,0.001421882,0.00005727934,0.0001777179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07018638,0.00001163786,0.9275889,0.0004642774,0.0005295611,0.0001633721,0.000001528945,0.0001238272,0.0009304894],"genre_scores_gemma":[0.9407119,0.000005203431,0.05850315,0.0002166269,0.00006336209,0.00000648345,0.000003232293,0.00001180829,0.0004782864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8705255,"threshold_uncertainty_score":0.5742378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02726780046543794,"score_gpt":0.2834111906519792,"score_spread":0.2561433901865413,"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."}}