{"id":"W4362656051","doi":"10.48550/arxiv.2304.01914","title":"Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; MIMO; Deep learning; Channel state information; Artificial neural network; Wireless network; Quantization (signal processing); Artificial intelligence; Computer engineering; Wireless; Machine learning; Channel (broadcasting); Computer network; Algorithm; Telecommunications","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":[0.0005792583,0.0006384116,0.0003834336,0.0003015912,0.0002508156,0.0004759121,0.000947643,0.0004532321,0.001970766],"category_scores_gemma":[0.00280069,0.0003032907,0.0002525662,0.0004470699,0.0004427204,0.001384141,0.0007770498,0.001659405,0.0004193994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007439743,"about_ca_system_score_gemma":0.001153672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007889692,"about_ca_topic_score_gemma":0.01691679,"domain_scores_codex":[0.9997659,0.00003715755,0.00001290042,0.00003418325,0.0001186529,0.00003117865],"domain_scores_gemma":[0.9992674,0.0003459142,0.00005957958,0.0001486415,0.0001526313,0.00002584205],"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":[0.0001837794,0.00008780532,0.00112085,0.0001054744,0.00004652697,0.000124515,0.00008563547,0.7934095,0.01771753,0.01159333,0.003585533,0.1719396],"study_design_scores_gemma":[0.00000334102,0.00001386099,0.00006999942,0.000003933033,0.000002791809,0.00001124805,0.000005174921,0.9935603,0.004027595,0.001874171,0.0004246455,0.000002786176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05391974,0.0004043259,0.9397531,0.0004829374,0.00009542223,0.00003901192,0.0002334368,0.002617261,0.002454793],"genre_scores_gemma":[0.7177614,0.0004245173,0.2781144,0.0002512205,0.00004563534,0.00008743976,0.0005377139,0.0001454294,0.002632257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007889692,"threshold_uncertainty_score":0.01568753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1128345694270069,"score_gpt":0.2133768730933847,"score_spread":0.1005423036663778,"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."}}