{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002624032,0.002361966,0.001495578,0.00103574,0.0007008938,0.001579077,0.002520791,0.001283436,0.001747907],"category_scores_gemma":[0.007078275,0.0008289337,0.0008013372,0.000625456,0.0007672459,0.004142056,0.002042466,0.002237605,0.0007169477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001518141,"about_ca_system_score_gemma":0.001664885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01119504,"about_ca_topic_score_gemma":0.01970019,"domain_scores_codex":[0.9987785,0.0003130308,0.00008021507,0.0003524907,0.0002676872,0.0002080345],"domain_scores_gemma":[0.9969242,0.001441426,0.0001508716,0.0005428982,0.0007499973,0.0001905477],"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":[0.0008319244,0.0002796236,0.003412696,0.0001259142,0.0001384553,0.0002417581,0.0001647277,0.6427006,0.01333741,0.005940568,0.00407617,0.3287501],"study_design_scores_gemma":[0.00001620307,0.00007652305,0.0002679625,0.00001135385,0.00002473489,0.00003396357,0.0000170252,0.9885855,0.005456645,0.004739683,0.0007571175,0.00001324248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04419904,0.0005288434,0.9474456,0.0002604212,0.0001052883,0.0001317983,0.0001154789,0.003899677,0.003313954],"genre_scores_gemma":[0.6754383,0.0003104862,0.3179018,0.0005921674,0.0001100101,0.0001357615,0.0008883976,0.0008384299,0.003784723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01119504,"threshold_uncertainty_score":0.02225977,"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."}}