{"id":"W4379522931","doi":"10.21428/594757db.acb1ea67","title":"Optimizing DNNs Model Partitioning for Enhanced Performance on Edge Devices","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Workload; Parallelism (grammar); Enhanced Data Rates for GSM Evolution; Data parallelism; Edge device; Reduction (mathematics); Task (project management); Parallel computing; Deep neural networks; Distributed computing; Artificial neural network; Computer engineering; Artificial intelligence; 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":[0.0000962488,0.00009665221,0.00008698315,0.00006753194,0.0003284197,0.00006546226,0.0004386012,0.0000270321,0.000003042199],"category_scores_gemma":[0.00001257532,0.00008963126,0.00003864197,0.0005166332,0.0000163805,0.0004923871,0.0001144892,0.00006525145,0.0001621731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002415721,"about_ca_system_score_gemma":0.00002063118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.074405e-7,"about_ca_topic_score_gemma":0.00000369009,"domain_scores_codex":[0.9990913,0.000006360178,0.0001474183,0.0003364554,0.0001159539,0.0003024561],"domain_scores_gemma":[0.9993335,0.0001684684,0.0000531157,0.0003375693,0.0000513146,0.00005601452],"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":[0.000003088036,0.00001057305,0.00001097543,0.000008893755,0.0000026303,1.400584e-7,0.0001609777,0.8922906,0.003215451,0.08703329,0.0007612627,0.0165021],"study_design_scores_gemma":[0.0001142656,0.00003717398,0.0001090832,0.00001698846,0.000001506313,3.59028e-7,0.000009233159,0.9556277,0.03905546,0.003802255,0.001110516,0.0001154891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03126149,0.000008935544,0.963719,0.000870434,0.00008343774,0.0002615356,0.000001554885,0.0007084666,0.003085117],"genre_scores_gemma":[0.7355444,0.00002654887,0.2622952,0.0005804707,0.00005195782,0.0003472452,0.000006568937,0.000009562207,0.001138044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7042829,"threshold_uncertainty_score":0.3655057,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05333885072025477,"score_gpt":0.3041997679785108,"score_spread":0.250860917258256,"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."}}