{"id":"W3012468284","doi":"10.1109/access.2020.2981411","title":"A Layer-Partitioning Approach for Faster Execution of Neural Network-Based Embedded Applications in Edge Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Ontario Institute of Technology","keywords":"Computer science; Artificial neural network; Internet of Things; Enhanced Data Rates for GSM Evolution; Layer (electronics); Edge computing; Latency (audio); Embedded system; Edge device; Distributed computing; Computer network; Cloud computing; Operating system; Artificial intelligence; Telecommunications","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":[0.0001240225,0.0001681359,0.0002454182,0.00006217412,0.0001464442,0.000108893,0.001149136,0.00007912108,0.000002377774],"category_scores_gemma":[0.00001426707,0.0001733103,0.00008891266,0.00139899,0.00005556851,0.0006769952,0.0001387029,0.0001784676,0.000001730935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003011855,"about_ca_system_score_gemma":0.00003654275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006005133,"about_ca_topic_score_gemma":0.000007991183,"domain_scores_codex":[0.9984653,0.00005577873,0.0004232368,0.0005275365,0.0001526975,0.0003754324],"domain_scores_gemma":[0.9988455,0.0002207716,0.0002392626,0.000471983,0.0001073928,0.0001150688],"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":[0.00002000198,0.00006103704,0.001959607,0.00003021351,0.000004756256,3.099008e-7,0.00007287913,0.9887477,0.0003517391,0.004644062,0.001084734,0.003022947],"study_design_scores_gemma":[0.0004565909,0.00003487641,0.001227338,0.00001192524,0.000008720345,6.893371e-7,0.000008591448,0.9941552,0.002115297,0.001241576,0.0005697872,0.0001694612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007042976,0.00008246787,0.9905127,0.0006420009,0.00007690259,0.001249435,0.000005322055,0.0001542425,0.0002339712],"genre_scores_gemma":[0.927517,0.000004145995,0.06944726,0.001216396,0.0003540069,0.001384895,0.00005157143,0.00001860348,0.000006104885],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9210654,"threshold_uncertainty_score":0.7067387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06386654883837793,"score_gpt":0.318396623293407,"score_spread":0.2545300744550291,"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."}}