{"id":"W2898018479","doi":"10.1109/ijcnn.2018.8489442","title":"Reducing SqueezeNet Storage Size with Depthwise Separable Convolutions","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Nvidia","keywords":"Convolutional neural network; Computer science; Reduction (mathematics); Inference; Algorithm; Artificial intelligence; Pattern recognition (psychology); Mathematics; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007352049,0.0001183179,0.0001022874,0.00003523203,0.000342874,0.0000722355,0.000562489,0.00003253111,0.0001006865],"category_scores_gemma":[0.00002154895,0.00009623494,0.00002327305,0.0006708442,0.0001434461,0.0004759376,0.000150571,0.00009712577,0.0002815966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005154265,"about_ca_system_score_gemma":0.00006881388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004011553,"about_ca_topic_score_gemma":0.00008657921,"domain_scores_codex":[0.9989398,0.00002590133,0.0001389598,0.0004263,0.0001560334,0.0003130224],"domain_scores_gemma":[0.9987509,0.000142565,0.00006266027,0.0008000236,0.0001229586,0.0001208652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005533551,0.0003587014,0.001283047,0.00001740417,0.00007777363,0.00003783302,0.001256408,0.04067069,0.02891672,0.7978619,0.1005301,0.02893399],"study_design_scores_gemma":[0.001500092,0.0008003116,0.007822624,0.00007192173,0.00003404053,0.0002605631,0.00008053734,0.7431161,0.03823406,0.0278468,0.1789062,0.001326731],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02210688,0.00003519962,0.9500319,0.001084427,0.0001130658,0.0002208094,0.000001383996,0.0005020382,0.02590428],"genre_scores_gemma":[0.7088696,0.000005045497,0.286663,0.0004706978,0.000132564,0.00004385228,9.269446e-7,0.000009587387,0.003804757],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7700151,"threshold_uncertainty_score":0.3924347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01373501367424318,"score_gpt":0.2576138056193586,"score_spread":0.2438787919451154,"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."}}