{"id":"W2007800125","doi":"10.1007/s10115-014-0801-8","title":"Greedy column subset selection for large-scale data sets","year":2014,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Column (typography); Selection (genetic algorithm); Greedy algorithm; Algorithm; Representation (politics); Matrix (chemical analysis); Big data; Data mining; Artificial intelligence; Frame (networking)","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":[0.002045721,0.001984775,0.003167829,0.002676265,0.001428328,0.001995054,0.002538315,0.001407676,0.004025536],"category_scores_gemma":[0.007130517,0.000928579,0.001990488,0.003800157,0.0008914231,0.001795366,0.001593214,0.001672889,0.002093735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005566605,"about_ca_system_score_gemma":0.002402544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00478381,"about_ca_topic_score_gemma":0.01049613,"domain_scores_codex":[0.9984737,0.0005299787,0.0001449562,0.0003221947,0.000338429,0.0001906912],"domain_scores_gemma":[0.9951853,0.003115656,0.000181202,0.0007955162,0.000499669,0.0002226656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001439646,0.0008857434,0.007488468,0.0007926346,0.0006231323,0.0005404422,0.0002598451,0.1773816,0.01991207,0.004072769,0.05562621,0.7309775],"study_design_scores_gemma":[0.0001620147,0.0002283987,0.001935819,0.00003903989,0.0001580921,0.0002502178,0.0002400074,0.9735112,0.006154989,0.0138457,0.003440113,0.00003427849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0808576,0.002150911,0.9026178,0.001302441,0.0002833099,0.0005031752,0.004837399,0.005789918,0.001657522],"genre_scores_gemma":[0.3958808,0.001054999,0.5665901,0.0008516598,0.0005967169,0.001084075,0.02807845,0.0007914052,0.005071898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00478381,"threshold_uncertainty_score":0.01346678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02411245776584549,"score_gpt":0.2674305953687463,"score_spread":0.2433181376029008,"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."}}