{"id":"W2967097710","doi":"","title":"Applications of Stochastic Gradient Descent to Nonnegative Matrix Factorization","year":2019,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Waterloo","keywords":"Non-negative matrix factorization; Stochastic gradient descent; Nonnegative matrix; Mathematics; Gradient descent; Matrix decomposition; Applied mathematics; Computer science; Artificial intelligence; Physics; Symmetric matrix","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002642121,0.0001684366,0.0002955421,0.0003071424,0.00004420575,0.000006439417,0.0002182692,0.0001539412,0.00002898319],"category_scores_gemma":[0.000003910796,0.0002104536,0.00008913797,0.0002196892,0.0000207284,0.00006584326,0.00002728103,0.00011758,0.00003211228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009168527,"about_ca_system_score_gemma":0.00002331777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002521364,"about_ca_topic_score_gemma":0.001929992,"domain_scores_codex":[0.9993832,0.00001304458,0.0001125603,0.0001841606,0.0001689382,0.0001380916],"domain_scores_gemma":[0.9993321,0.00002099258,0.0001205776,0.0002691348,0.0002014681,0.00005566815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004922695,0.0004098669,0.0003222292,0.002822014,0.001153574,0.00001493237,0.442628,0.157531,0.3521257,0.004514803,0.007188996,0.0307966],"study_design_scores_gemma":[0.002587489,0.001298504,0.01171916,0.005647915,0.001847423,0.000006942151,0.3717178,0.06846444,0.5261583,0.002707854,0.003885577,0.003958571],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8744451,0.00009467072,0.123481,0.00003256245,0.0002908079,0.000977096,0.00008690232,0.0002387352,0.0003531431],"genre_scores_gemma":[0.9741361,0.00003348709,0.003309175,0.000001721596,0.00001846483,0.000001856841,0.0003362613,0.00003313446,0.02212985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1740326,"threshold_uncertainty_score":0.8582048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007462764895009489,"score_gpt":0.2049454889177475,"score_spread":0.197482724022738,"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."}}