{"id":"W3009178287","doi":"10.1109/tpami.2020.2978812","title":"Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Image and Object Detection Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"National Major Science and Technology Projects of China; Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Eigendecomposition of a matrix; Eigenvalues and eigenvectors; Computer science; Algorithm; Artificial intelligence; Outlier; Linear system; Ellipse; Applied mathematics; Mathematical optimization; Mathematics","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":[0.001689365,0.001703587,0.0008780868,0.0005043871,0.0004342797,0.000666438,0.001516038,0.00162794,0.003466962],"category_scores_gemma":[0.00677694,0.0008354416,0.0005436883,0.0005134715,0.001037881,0.001522714,0.001607741,0.003172825,0.00105471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009267136,"about_ca_system_score_gemma":0.001437128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003789437,"about_ca_topic_score_gemma":0.008161825,"domain_scores_codex":[0.999431,0.0001926345,0.00003482999,0.0001269021,0.0001341638,0.00008049575],"domain_scores_gemma":[0.998004,0.001192265,0.0001303896,0.0002171796,0.0003783141,0.00007783321],"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":[0.0001386517,0.0001147768,0.0007526367,0.00008126368,0.00004487349,0.00005884788,0.00007340727,0.8573593,0.005853706,0.00804992,0.002557178,0.1249155],"study_design_scores_gemma":[0.000004070105,0.00001286117,0.00002521828,0.000003071111,0.000001315594,0.000004621966,0.000003531093,0.9973948,0.0007194128,0.00169094,0.0001384234,0.000001702634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0177307,0.0001798607,0.9796932,0.0001887529,0.00003094823,0.00003884816,0.00004291757,0.001039578,0.001055326],"genre_scores_gemma":[0.4292264,0.0002326495,0.5640562,0.0004095057,0.00006214275,0.0004036284,0.0006169219,0.0003485668,0.00464404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003789437,"threshold_uncertainty_score":0.01159817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02930564398049754,"score_gpt":0.2673396138684919,"score_spread":0.2380339698879944,"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."}}