{"id":"W2998159825","doi":"","title":"Deep Learning Inference Frameworks for ARM CPU","year":2019,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Inference; Server; Usability; Enhanced Data Rates for GSM Evolution; Central processing unit; Adaptation (eye); Edge device; Deep learning; Artificial intelligence; Edge computing; Machine learning; Human–computer interaction; Cloud computing; Operating system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026981,0.001305637,0.0007252708,0.0007661482,0.0004498024,0.001665985,0.003489912,0.001298722,0.01989189],"category_scores_gemma":[0.00439906,0.0008118469,0.001225677,0.0008562073,0.0005499832,0.001827972,0.00184088,0.003090356,0.00831042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001583051,"about_ca_system_score_gemma":0.001847943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01259845,"about_ca_topic_score_gemma":0.01523131,"domain_scores_codex":[0.9992062,0.000106957,0.00006417205,0.0001870146,0.0003231838,0.0001124206],"domain_scores_gemma":[0.9991246,0.0002335464,0.00005553084,0.0002280891,0.0003127886,0.00004549296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004882945,0.0001668716,0.001402464,0.0004445314,0.0001708831,0.0002020587,0.0001466613,0.3089022,0.008558768,0.1446192,0.08975846,0.4451397],"study_design_scores_gemma":[0.00003164625,0.00002446079,0.0002066145,0.0000475091,0.00002180637,0.00006180698,0.00001378397,0.9329907,0.005285063,0.03620307,0.02509008,0.00002345062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001928098,0.0006079563,0.9712971,0.0003378622,0.0001077785,0.00006277351,0.0006241802,0.01963063,0.005403651],"genre_scores_gemma":[0.1264375,0.001181454,0.8427385,0.0006940892,0.0001583421,0.0005797339,0.004020363,0.003418536,0.02077139],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01989189,"threshold_uncertainty_score":0.06654501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008470528831988292,"score_gpt":0.2939385152586868,"score_spread":0.2854679864266985,"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."}}