{"id":"W3059280052","doi":"10.1109/tii.2020.3017573","title":"Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Edge computing; Inference; Markov decision process; Lyapunov optimization; Enhanced Data Rates for GSM Evolution; Edge device; Task (project management); Artificial intelligence; Distributed computing; Machine learning; Markov process; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005214553,0.0003737396,0.0004703749,0.000372914,0.0004135763,0.0004039218,0.0009195517,0.00044433,0.00002726715],"category_scores_gemma":[0.0003573466,0.0003782028,0.0001200322,0.002342934,0.00007105659,0.001030339,0.00002789602,0.002060829,0.0001751233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002519433,"about_ca_system_score_gemma":0.0005999976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006203623,"about_ca_topic_score_gemma":0.000007631106,"domain_scores_codex":[0.996985,0.0001795021,0.001337674,0.0002802254,0.0006074262,0.0006101475],"domain_scores_gemma":[0.9977993,0.0009085998,0.0004965155,0.0003616463,0.0001681335,0.0002658356],"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":[0.0002071917,0.00008035901,0.00009871852,0.00002084083,0.00006206353,0.00001074794,0.02131606,0.7922455,0.00009198574,0.0001260054,0.0009368333,0.1848037],"study_design_scores_gemma":[0.003681422,0.0007670089,0.000004346134,0.0001319293,0.00002161988,0.000004929737,0.0009494119,0.9748349,0.00837985,0.00003595122,0.01069769,0.0004909651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02306076,0.000007264114,0.9681164,0.0007307267,0.006067664,0.0007200385,0.000001477031,0.0002803681,0.001015312],"genre_scores_gemma":[0.9950985,0.00001471375,0.002689579,0.001004152,0.001090132,0.00004018165,0.000005684085,0.00001857541,0.00003852227],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9720377,"threshold_uncertainty_score":0.999867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06671552464797127,"score_gpt":0.2770277306532551,"score_spread":0.2103122060052838,"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."}}