{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001813114,0.0001875646,0.0003536115,0.0002929158,0.0001782439,0.00006814455,0.0004960984,0.00007182438,0.00005114635],"category_scores_gemma":[0.000007511106,0.0001738803,0.0003400033,0.000971427,0.00004728348,0.0002211958,0.000007734664,0.0002112522,0.000002440927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000158221,"about_ca_system_score_gemma":0.00001399349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001879012,"about_ca_topic_score_gemma":0.0003293687,"domain_scores_codex":[0.9986827,0.00005366759,0.0004307251,0.0004395943,0.0001845219,0.0002087268],"domain_scores_gemma":[0.9991044,0.0001196456,0.0001419519,0.000380685,0.0001298315,0.0001234818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001882749,0.00006785919,0.00003525039,0.00004783974,0.0002833,0.000001988428,0.001263864,0.1062914,0.0005546901,0.00003567646,0.000006438956,0.8913929],"study_design_scores_gemma":[0.00009040856,0.0003343142,0.00003439711,0.00001575422,0.000177936,0.000003923104,0.00007443895,0.7182118,0.2806252,0.0002437424,0.00003740327,0.0001507616],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002186067,0.0001181595,0.9985157,0.0005885823,0.00008222701,0.0002444173,0.00003931449,0.0001582885,0.00003473763],"genre_scores_gemma":[0.9822404,0.0001449725,0.0168206,0.0006661269,0.00003857636,0.00005522032,0.000005958769,0.00001255578,0.00001554931],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9820218,"threshold_uncertainty_score":0.7090633,"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."}}