{"id":"W2976146566","doi":"10.3390/fi11100209","title":"Partitioning Convolutional Neural Networks to Maximize the Inference Rate on Constrained IoT Devices","year":2019,"lang":"en","type":"article","venue":"Future Internet","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Inference; Convolutional neural network; Artificial intelligence; Internet of Things; Machine learning; Computer network; Distributed computing; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0009305,0.001189316,0.0009316755,0.0004358268,0.0006271253,0.0009634951,0.001407415,0.0008189642,0.001994078],"category_scores_gemma":[0.00533061,0.0006431432,0.0004773394,0.0003991798,0.0007636746,0.00285781,0.001351303,0.001388195,0.0003103545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002005355,"about_ca_system_score_gemma":0.001441112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008112886,"about_ca_topic_score_gemma":0.01394888,"domain_scores_codex":[0.9995412,0.0001109138,0.00002543391,0.0001218405,0.00008418215,0.0001166353],"domain_scores_gemma":[0.9988506,0.0006367704,0.0001015629,0.0001690363,0.0001667077,0.00007536986],"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":[0.0002945673,0.0000924561,0.001108885,0.00004675069,0.00004049788,0.00008389459,0.00008589704,0.9342872,0.004869172,0.005888938,0.001687041,0.05151468],"study_design_scores_gemma":[0.000006194122,0.00001084205,0.00007392915,0.000002776073,0.000003414699,0.000007245379,0.00001090948,0.9961529,0.001352469,0.002252436,0.0001246757,0.000002164268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2231212,0.0003717801,0.7685357,0.000596154,0.0000623804,0.0001330109,0.000176084,0.001661324,0.005342385],"genre_scores_gemma":[0.8724732,0.0001173682,0.1242151,0.0001895264,0.00002278877,0.0001003607,0.0002407806,0.0001882708,0.002452517],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008112886,"threshold_uncertainty_score":0.01613128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01273240198646072,"score_gpt":0.2375572596197771,"score_spread":0.2248248576333164,"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."}}