{"id":"W4313546834","doi":"10.1109/access.2023.3234245","title":"PANCODE: Multilevel Partitioning of Neural Networks for Constrained Internet-of-Things Devices","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":4,"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; Distributed computing; Cloud computing; Edge device; Edge computing; Convolutional neural network; Enhanced Data Rates for GSM Evolution; Inference; Partition (number theory); Artificial intelligence","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":[0.0003522162,0.0008921411,0.0005285728,0.0004876214,0.000565825,0.000623662,0.001334174,0.0006437433,0.001815162],"category_scores_gemma":[0.001623101,0.0003673632,0.0005355,0.0003048294,0.0003869971,0.00136031,0.001379571,0.001035066,0.0003778664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000944282,"about_ca_system_score_gemma":0.001059548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007491911,"about_ca_topic_score_gemma":0.01652115,"domain_scores_codex":[0.9998123,0.00002980034,0.00001014768,0.00005668036,0.00005337704,0.00003769315],"domain_scores_gemma":[0.9997358,0.00008807587,0.00002971273,0.00005864713,0.00005949091,0.00002830953],"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":[0.0002366734,0.0001201681,0.002216666,0.00008968025,0.0001043452,0.0001384551,0.0001396266,0.6804601,0.01250235,0.009793887,0.00664456,0.2875535],"study_design_scores_gemma":[0.000007641664,0.00002700311,0.0001463877,0.000004482401,0.000005976092,0.00001991172,0.00001537695,0.9939972,0.002323722,0.002678599,0.0007702822,0.000003470194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08412533,0.0003825146,0.9080222,0.000329293,0.00007869901,0.0001226521,0.0002102109,0.002915506,0.003813621],"genre_scores_gemma":[0.557655,0.0001630612,0.4372227,0.0002304686,0.00002714953,0.0001991419,0.0008222892,0.0003026121,0.003377621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007491911,"threshold_uncertainty_score":0.01489663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06733315968609746,"score_gpt":0.3295190261027127,"score_spread":0.2621858664166152,"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."}}