{"id":"W3040368914","doi":"10.1109/twc.2021.3080672","title":"Unsupervised Deep Learning for Massive MIMO Hybrid Beamforming","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Advanced MIMO Systems Optimization","field":"Engineering","cited_by":90,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Codebook; Beamforming; Deep learning; MIMO; Channel state information; Precoding; Unsupervised learning; Synchronization (alternating current); Spectral efficiency","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":[0.000464679,0.0007636222,0.0005097531,0.0002649162,0.0002116586,0.0004088409,0.0007994164,0.0006533406,0.001421897],"category_scores_gemma":[0.00120833,0.0003626093,0.0003853185,0.0004185482,0.0004731536,0.0007190292,0.0007723336,0.001129554,0.0004697671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004430546,"about_ca_system_score_gemma":0.0006146893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002202699,"about_ca_topic_score_gemma":0.004889403,"domain_scores_codex":[0.9998026,0.00005491747,0.00000869242,0.00004023588,0.00006221618,0.0000313578],"domain_scores_gemma":[0.9995914,0.0001973882,0.00004323958,0.00004160753,0.0001035945,0.00002279348],"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":[0.00006612183,0.00007282924,0.0005063079,0.0000641285,0.00006784387,0.00004349385,0.00003377359,0.8276795,0.007982809,0.01168327,0.002506524,0.1492934],"study_design_scores_gemma":[0.000002131803,0.000009089877,0.00002709516,0.000001260237,0.000001680766,0.000004011018,0.00000156892,0.9975917,0.0005561193,0.001652624,0.0001507057,0.000001963601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006582024,0.0001168155,0.9918515,0.00008680585,0.00001511703,0.00001011464,0.00004245704,0.0003809112,0.0009142195],"genre_scores_gemma":[0.6216879,0.0003068922,0.3708482,0.0003214518,0.00007396199,0.0001562562,0.0004023774,0.000122021,0.006080941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002202699,"threshold_uncertainty_score":0.004756749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01892477748231792,"score_gpt":0.2488282261060518,"score_spread":0.2299034486237339,"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."}}