{"id":"W2896457526","doi":"10.1109/ijcnn.2018.8489242","title":"Nonnegative Matrix Factorization Using Autoencoders And Exponentiated Gradient Descent","year":2018,"lang":"en","type":"article","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Non-negative matrix factorization; Matrix decomposition; Gradient descent; Cluster analysis; Computer science; Factorization; Basis (linear algebra); Stochastic gradient descent; Artificial intelligence; Matrix (chemical analysis); Pattern recognition (psychology); Image (mathematics); Algorithm; Hierarchy; Encoder; Mathematics; Deep learning; Artificial neural network","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":[0.00006492992,0.00007526146,0.00006604152,0.00007537311,0.0001578081,0.0001043743,0.00011053,0.00003526727,0.00005151037],"category_scores_gemma":[0.00001330527,0.00006137681,0.00001596391,0.0001880304,0.00004178304,0.0004859096,0.00009142685,0.00003330175,0.00003873628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002709018,"about_ca_system_score_gemma":0.0000175984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006250389,"about_ca_topic_score_gemma":0.00001131586,"domain_scores_codex":[0.9993696,0.00003349241,0.0001097578,0.0002177778,0.0001265834,0.0001427395],"domain_scores_gemma":[0.999651,0.00001569677,0.00004800473,0.000123872,0.0000948951,0.00006649664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001877859,0.0009466976,0.01771714,0.0001567135,0.0002317028,0.0000437816,0.04848688,0.001550151,0.7137339,0.0598603,0.01206755,0.1450174],"study_design_scores_gemma":[0.0003739644,0.0001426458,0.002369263,0.00005209087,0.000007153333,0.000008769724,0.000244313,0.8768423,0.1167195,0.002678057,0.0003706513,0.0001913184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2850747,0.0000097882,0.7141294,0.0001161723,0.0002403441,0.00007681808,6.751275e-7,0.00008785183,0.0002642635],"genre_scores_gemma":[0.8973827,0.000008548132,0.1023868,0.00009661654,0.00003194985,0.000002131525,0.000002987731,0.000003659393,0.00008458934],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8752921,"threshold_uncertainty_score":0.2502874,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02788483744999191,"score_gpt":0.2806034847195265,"score_spread":0.2527186472695346,"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."}}