{"id":"W3009189291","doi":"10.1109/globecom38437.2019.9014224","title":"Adaptive Content Placement in Edge Networks Based on Hybrid User Preference Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Backhaul (telecommunications); Stochastic gradient descent; Enhanced Data Rates for GSM Evolution; Hybrid learning; Latency (audio); Gradient descent; Cloud computing; Artificial intelligence; Content delivery; Artificial neural network; Machine learning; Computer network; Base station","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008224322,0.0007160242,0.001108819,0.0004644264,0.0004014351,0.0007025774,0.001662268,0.0009367722,0.0007079614],"category_scores_gemma":[0.002892411,0.0003885879,0.0003467073,0.0008378999,0.0006048455,0.001512557,0.0008830152,0.0007303965,0.0002111509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008473961,"about_ca_system_score_gemma":0.0009087374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006964699,"about_ca_topic_score_gemma":0.007906862,"domain_scores_codex":[0.999373,0.000182926,0.00002933528,0.0001611569,0.0001347937,0.000118847],"domain_scores_gemma":[0.9985126,0.0007696184,0.0001536383,0.0001102076,0.0003574746,0.00009650255],"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":[0.0002268957,0.0001495887,0.003821289,0.00005086213,0.00006043698,0.0001101405,0.00008312837,0.9004107,0.004097403,0.003792305,0.001485927,0.0857113],"study_design_scores_gemma":[0.000003905145,0.00001375357,0.00008356586,7.527703e-7,0.000002472213,0.000009794078,0.000003878588,0.9989257,0.0003471789,0.0005595671,0.00004689377,0.000002515109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08014718,0.0002486032,0.9179559,0.000182068,0.00003136272,0.0000450132,0.0000503052,0.0003767687,0.0009626857],"genre_scores_gemma":[0.931594,0.0001336556,0.06628251,0.0001596586,0.00003781689,0.00005799693,0.00008259172,0.000027822,0.001623866],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006964699,"threshold_uncertainty_score":0.01384836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04732878300822285,"score_gpt":0.2101738533164994,"score_spread":0.1628450703082766,"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."}}