{"id":"W3166653712","doi":"10.1109/jsac.2021.3087234","title":"Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment","year":2021,"lang":"en","type":"article","venue":"IEEE Journal on Selected Areas in Communications","topic":"Millimeter-Wave Propagation and Modeling","field":"Engineering","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Computer science; Beamforming; Fading; Adaptive beamformer; Channel state information; Channel (broadcasting); Artificial neural network; Algorithm; Artificial intelligence; Telecommunications; Wireless","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006663942,0.0007367529,0.0005701855,0.0003580782,0.0002423855,0.0005679869,0.001200899,0.000938256,0.001939625],"category_scores_gemma":[0.001406195,0.0004404171,0.0004337384,0.0004530438,0.0005940642,0.001059036,0.0008185702,0.001749086,0.0003352239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006538,"about_ca_system_score_gemma":0.00077506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003035055,"about_ca_topic_score_gemma":0.0048299,"domain_scores_codex":[0.9997532,0.00006817203,0.00001359239,0.00005454298,0.00007445996,0.00003606257],"domain_scores_gemma":[0.9995246,0.0002728984,0.0000435353,0.00002891333,0.0001082754,0.00002179059],"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":[0.00007132834,0.00005302254,0.0004652851,0.00007512244,0.00004282295,0.00004627713,0.00005336273,0.8339925,0.005572833,0.0257499,0.001400269,0.1324773],"study_design_scores_gemma":[0.000001846074,0.000007022405,0.00002026114,0.000002077594,0.000001840895,0.000004068293,0.000001965685,0.9965354,0.0004974756,0.002634484,0.0002918298,0.000001766442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002036171,0.0001199967,0.9969367,0.00007509276,0.00001507045,0.000006341022,0.00001512447,0.00007763031,0.0007179421],"genre_scores_gemma":[0.5530521,0.0008286288,0.4365005,0.0003911777,0.000149174,0.0001686753,0.0002003848,0.00009448399,0.008614852],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003035055,"threshold_uncertainty_score":0.006488681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06350940356307683,"score_gpt":0.2981327057581407,"score_spread":0.2346233021950638,"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."}}