{"id":"W4312845220","doi":"10.1109/asap54787.2022.00020","title":"Fast Heterogeneous Task Mapping for Reducing Edge DNN Latency","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies","keywords":"Computer science; Initialization; Inference; Latency (audio); Edge computing; Task (project management); Enhanced Data Rates for GSM Evolution; Parallel computing; Distributed computing; Artificial intelligence","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":[0.00007523134,0.0001006094,0.0001065293,0.00004993193,0.0002756952,0.00001164729,0.0001124373,0.00001568159,0.00009432097],"category_scores_gemma":[0.00001001781,0.0001097438,0.00006078083,0.0001138624,0.000005567179,0.00006052824,0.0000795267,0.0001365389,0.000006566202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006394329,"about_ca_system_score_gemma":0.000005354634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000127591,"about_ca_topic_score_gemma":5.547207e-7,"domain_scores_codex":[0.9993553,0.00001041719,0.0001522193,0.0001616887,0.00006684774,0.00025353],"domain_scores_gemma":[0.9997497,0.00005721797,0.00001794969,0.0001245634,0.000009736826,0.00004080654],"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":[0.000004504056,0.000006398597,0.000008053272,0.00004433463,0.00001193379,0.00001044582,0.0002572487,0.8513366,0.123485,0.00008089889,0.0004457876,0.02430883],"study_design_scores_gemma":[0.0007440673,0.0001921179,0.00004716159,0.00003798657,0.00001728922,0.0002449125,0.0006764314,0.6916809,0.2320747,0.00116793,0.07236029,0.0007562201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8438568,0.0004065993,0.1497993,0.00005514356,0.001159916,0.0003075147,0.00001419889,0.0008226068,0.003577922],"genre_scores_gemma":[0.9951507,0.000005239994,0.003769344,0.00009201117,0.0001488203,0.00004741623,0.000008885585,0.0000325747,0.0007450503],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1596557,"threshold_uncertainty_score":0.4475221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02119805558447708,"score_gpt":0.2248744716856532,"score_spread":0.2036764161011761,"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."}}