{"id":"W3105027165","doi":"","title":"Regularized linear autoencoders recover the principal components, eventually","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regularization (linguistics); Feature learning; Computer science; Simple (philosophy); Representation (politics); Principal component analysis; Gradient descent; Mathematical optimization; Mathematics; Artificial intelligence; Artificial neural network; Algorithm; Applied 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":[0.001777712,0.001304023,0.0006621327,0.000650357,0.0003859271,0.001259177,0.001025669,0.00103902,0.003439154],"category_scores_gemma":[0.008406925,0.0008312133,0.000708289,0.0007587766,0.001319395,0.003105649,0.00136194,0.002782347,0.00220655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006457314,"about_ca_system_score_gemma":0.001131147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002342119,"about_ca_topic_score_gemma":0.003614773,"domain_scores_codex":[0.9993085,0.0001990793,0.0000419724,0.0002224256,0.0001657092,0.00006238382],"domain_scores_gemma":[0.9982073,0.000689455,0.0001666763,0.0005401009,0.0003494048,0.00004705566],"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":[0.0001744846,0.0000744214,0.002256111,0.0002234629,0.0001957893,0.0001285969,0.0002147254,0.4396412,0.01354162,0.2371855,0.009592048,0.2967721],"study_design_scores_gemma":[0.000008494797,0.00003003607,0.0006057558,0.00002771458,0.00001736323,0.00004525405,0.00002103317,0.899099,0.004549004,0.09036694,0.005214238,0.0000152216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007778968,0.0002866351,0.9890817,0.0002598614,0.00005916465,0.00002014595,0.0001219361,0.000555936,0.001835584],"genre_scores_gemma":[0.3519361,0.0009360944,0.6284795,0.000395987,0.0001837193,0.0001336511,0.000723888,0.0004742233,0.01673691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003439154,"threshold_uncertainty_score":0.01150513,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03675184295725883,"score_gpt":0.2432656193508974,"score_spread":0.2065137763936386,"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."}}