{"id":"W4293232522","doi":"10.1145/3517206.3526270","title":"Combining DNN partitioning and early exit","year":2022,"lang":"en","type":"article","venue":"","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Huawei Technologies","keywords":"Computer science; Inference; Flexibility (engineering); Server; Software deployment; Computation; Latency (audio); Distributed computing; Enhanced Data Rates for GSM Evolution; Process (computing); Real-time computing; Artificial intelligence; Algorithm; Computer network; Operating system","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":[0.0002572124,0.00005346465,0.00006657154,0.00009011565,0.0005670867,0.0001682619,0.0002630203,0.000009107298,0.0000175186],"category_scores_gemma":[0.000008803029,0.0000558961,0.00001870421,0.0003070321,0.00001380942,0.0002095301,0.0007238284,0.0001158159,0.00001302872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001373747,"about_ca_system_score_gemma":0.00001553752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005946445,"about_ca_topic_score_gemma":4.458028e-7,"domain_scores_codex":[0.9993612,0.00003936997,0.0001024371,0.0001913247,0.0001207164,0.0001849374],"domain_scores_gemma":[0.999705,0.00005274748,0.00003050709,0.0001526145,0.00001322181,0.00004595131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001369874,0.0002053408,0.2684101,0.00003530097,0.00006451366,0.0001361585,0.02562614,0.0009297747,0.001278989,0.382278,0.1303227,0.1906993],"study_design_scores_gemma":[0.001533278,0.0007297146,0.09687492,0.00003709556,0.00001214738,0.0002556649,0.0005023363,0.5566373,0.001224142,0.04727015,0.2938977,0.001025544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8107499,0.0001311642,0.1429981,0.0009981999,0.004390495,0.00007125871,3.977453e-8,0.000356991,0.04030379],"genre_scores_gemma":[0.9890673,0.000001401233,0.009468358,0.000360075,0.0002271228,0.000008119129,4.306774e-7,0.000004528898,0.0008626262],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5557075,"threshold_uncertainty_score":0.436163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01783931017237814,"score_gpt":0.2168590373089303,"score_spread":0.1990197271365521,"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."}}