{"id":"W3117570688","doi":"10.1109/ojcas.2020.3047418","title":"Hardware-Aware Design for Edge Intelligence","year":2020,"lang":"en","type":"article","venue":"IEEE Open Journal of Circuits and Systems","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Software deployment; Enhanced Data Rates for GSM Evolution; Inference; Edge device; Cloud computing; Latency (audio); Edge computing; Deep neural networks; Server; Bandwidth (computing); Distributed computing; Computer architecture; Computer network; Artificial intelligence; Artificial neural network; Telecommunications; Software engineering; 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":[0.0003321207,0.0001013033,0.0002943796,0.00002684809,0.00007113119,0.0001475282,0.0002841641,0.00003418951,0.000003307986],"category_scores_gemma":[0.00004020852,0.00008398295,0.000045003,0.00007332338,0.00001096989,0.0003150839,0.00001660987,0.0001360196,0.000002653577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001450449,"about_ca_system_score_gemma":0.00001996119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.388608e-7,"about_ca_topic_score_gemma":1.081042e-7,"domain_scores_codex":[0.9992627,0.00003555425,0.0003807358,0.00009143891,0.00008981984,0.0001397539],"domain_scores_gemma":[0.9994273,0.0001435943,0.000120996,0.00005828071,0.00009695224,0.0001529472],"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":[0.00006661138,0.00001335784,0.00004614406,0.0007480781,0.0001192623,0.0001045651,0.002226274,0.8692344,0.05350806,0.0003243677,0.005292733,0.06831608],"study_design_scores_gemma":[0.00242787,0.002333078,0.00007377422,0.002283795,0.0001507741,0.001777969,0.00354475,0.6756886,0.2485134,0.0009104416,0.06106317,0.001232428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02131042,0.001679189,0.9750932,0.00005656516,0.001186164,0.0003807694,0.000005369797,0.00002064453,0.0002676319],"genre_scores_gemma":[0.9990044,0.00007931623,0.0002948643,0.00006410484,0.0004943934,0.000004254662,2.350321e-7,0.00001902089,0.00003936177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.977694,"threshold_uncertainty_score":0.3424725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1555930611944083,"score_gpt":0.3026185713682348,"score_spread":0.1470255101738265,"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."}}