{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001288284,0.001374961,0.001172142,0.0006593836,0.0003802708,0.000891666,0.001338826,0.00109523,0.00183079],"category_scores_gemma":[0.004034796,0.0006841759,0.001002016,0.0006678302,0.0008202642,0.001563804,0.00103046,0.002102174,0.001197905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007177561,"about_ca_system_score_gemma":0.001070834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005740596,"about_ca_topic_score_gemma":0.008838123,"domain_scores_codex":[0.9994292,0.0001714569,0.00003822993,0.0001316582,0.0001798,0.00004969369],"domain_scores_gemma":[0.998728,0.000619339,0.000142505,0.0001811735,0.0002786244,0.00005043945],"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":[0.0000786036,0.00008893984,0.0007150297,0.0001376545,0.0001142899,0.0001184376,0.0001037933,0.7068596,0.008225474,0.03505198,0.004021761,0.2444845],"study_design_scores_gemma":[0.00000364842,0.000009278821,0.00004019792,0.000004312514,0.000002470284,0.00001267214,0.000002127455,0.9950069,0.0006445759,0.003866781,0.0004032862,0.000003597562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001458935,0.00006817525,0.9978905,0.00003671243,0.0000186512,0.00001640141,0.00001531465,0.0001975192,0.0002977892],"genre_scores_gemma":[0.1126021,0.000275138,0.8832385,0.0001362558,0.00008421009,0.0001745496,0.0002554085,0.0001683175,0.003065415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005740596,"threshold_uncertainty_score":0.01141435,"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."}}